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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RESID-POST-AA
    6. 41352
    Prev
    Next
    INDEX
    Explanations

    start

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arter
    -0.08
     Trend
    -0.08
     conten
    -0.07
    票价
    -0.07
    辅助
    -0.07
     booster
    -0.07
    衬
    -0.07
     القط
    -0.07
     Esk
    -0.07
    ="'
    -0.07
    POSITIVE LOGITS
     yürüt
    0.08
     helium
    0.07
    .ButterKnife
    0.07
    กระทรว
    0.07
    셜
    0.07
    如何
    0.07
    _PW
    0.07
    WithDuration
    0.07
    ᓕ
    0.07
    	HRESULT
    0.07
    Activations Density 0.022%

    No Known Activations