© 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. 12225
    Prev
    Next
    INDEX
    Explanations

    Subtitles

    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
     pec
    -0.07
    Beyond
    -0.07
    .Byte
    -0.07
     diffs
    -0.07
    itti
    -0.07
     primitives
    -0.07
     yeti
    -0.07
    NECTION
    -0.07
    脯
    -0.06
     pled
    -0.06
    POSITIVE LOGITS
    っていう
    0.07
     imagen
    0.07
     então
    0.07
    這個
    0.07
    0.07
    都需要
    0.07
    ترة
    0.06
    过来
    0.06
    宝安
    0.06
    固定的
    0.06
    Activations Density 0.015%

    No Known Activations