© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 109688
    Prev
    Next
    INDEX
    Explanations

    booking travel

    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
    _video
    -0.07
    𦝼
    -0.07
     ofType
    -0.07
     Ger
    -0.07
    ORIZED
    -0.06
    xyz
    -0.06
    Assertions
    -0.06
    ество
    -0.06
     conten
    -0.06
    ATIVE
    -0.06
    POSITIVE LOGITS
    管家
    0.07
    战绩
    0.07
    珩
    0.07
    กระแ
    0.07
    _bloc
    0.06
     закон
    0.06
    伴
    0.06
    encoder
    0.06
    パターン
    0.06
    mvc
    0.06
    Activations Density 0.023%

    No Known Activations