© 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. 69849
    Prev
    Next
    INDEX
    Explanations

    American

    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
    Ё
    -0.07
    TB
    -0.07
    ilver
    -0.07
    毓
    -0.07
    示范基地
    -0.06
     bà
    -0.06
     IW
    -0.06
    Gateway
    -0.06
     Century
    -0.06
     contag
    -0.06
    POSITIVE LOGITS
     viewed
    0.09
    频繁
    0.07
    _requests
    0.07
     overlooking
    0.07
     namoro
    0.07
    稳妥
    0.07
    剥离
    0.07
    小孩
    0.07
     qualifications
    0.07
     Marble
    0.07
    Activations Density 0.022%

    No Known Activations