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

    Neuronpedia

    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. 23323
    Prev
    Next
    INDEX
    Explanations

    Free online content

    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
     Fair
    -0.07
    ऐ
    -0.07
    本事
    -0.07
     horn
    -0.07
    凇
    -0.06
    -pr
    -0.06
     thỏ
    -0.06
    -def
    -0.06
     sovereign
    -0.06
     stati
    -0.06
    POSITIVE LOGITS
    𫘜
    0.07
    (headers
    0.07
    (project
    0.07
    За
    0.07
    ｂ
    0.06
     PEN
    0.06
    메
    0.06
     raping
    0.06
     Meta
    0.06
    𝗻
    0.06
    Activations Density 0.020%

    No Known Activations