© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 75313
    Prev
    Next
    INDEX
    Explanations

    rejection/failure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蕨
    -0.07
     reuseIdentifier
    -0.07
    渫
    -0.07
    持续推进
    -0.07
    换来
    -0.07
    揭开
    -0.06
     раствор
    -0.06
     cousin
    -0.06
     artisan
    -0.06
    のみ
    -0.06
    POSITIVE LOGITS
    拥挤
    0.07
    олод
    0.07
    养猪
    0.07
     strongest
    0.07
     Epid
    0.07
     VGA
    0.06
     alarmed
    0.06
    붐
    0.06
    =ax
    0.06
    存款
    0.06
    Activations Density 0.031%

    No Known Activations