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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23-RESID-POST-AA
    6. 469
    Prev
    Next
    INDEX
    Explanations

    say JavaScript

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _gpu
    -0.07
     predicted
    -0.07
    _Pro
    -0.07
    	bus
    -0.06
     evolution
    -0.06
    aus
    -0.06
    同樣
    -0.06
    ]*
    -0.06
    辦理
    -0.06
     ≤
    -0.06
    POSITIVE LOGITS
    HTTPRequestOperation
    0.09
    枧
    0.08
     fotoğ
    0.07
     Kohana
    0.07
    🗯
    0.07
     sesame
    0.07
     columnHeader
    0.07
    金山
    0.07
    磉
    0.07
    海外市场
    0.07
    Activations Density 0.000%

    No Known Activations