© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 51422
    Prev
    Next
    INDEX
    Explanations

    capacitor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yt
    -0.07
    Convertible
    -0.07
    MouseButton
    -0.07
    &R
    -0.07
     Hib
    -0.07
    焦
    -0.07
    Into
    -0.07
     strands
    -0.07
     =============================================================================↵
    -0.07
     Highlights
    -0.07
    POSITIVE LOGITS
    MAS
    0.07
    믄
    0.07
    ﰼ
    0.07
     Representative
    0.07
    容纳
    0.07
    egen
    0.06
     detect
    0.06
    ですか
    0.06
    Conexion
    0.06
    	total
    0.06
    Activations Density 0.005%

    No Known Activations