Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 5509
    Prev
    Next
    INDEX
    Explanations

    code and copyright

    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
     categorie
    -0.08
    王爷
    -0.07
     France
    -0.07
    ภา
    -0.07
     хоро
    -0.06
    olg
    -0.06
    佐
    -0.06
     sociedad
    -0.06
    	json
    -0.06
    '";
    ↵
    -0.06
    POSITIVE LOGITS
    景区
    0.07
     encompass
    0.07
    规划设计
    0.07
    ᠄
    0.07
    gons
    0.07
    FormattedMessage
    0.07
    🏦
    0.07
    /pkg
    0.06
    _InitStruct
    0.06
    ups
    0.06
    Activations Density 0.101%

    No Known Activations