© 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. 8709
    Prev
    Next
    INDEX
    Explanations

    prefixes and suffixes

    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
    枷
    -0.07
    新闻中心
    -0.07
    繳
    -0.07
    opus
    -0.07
    ۑ
    -0.06
    collectionView
    -0.06
    运用
    -0.06
     наибол
    -0.06
     basic
    -0.06
     communicate
    -0.06
    POSITIVE LOGITS
    抗生素
    0.07
    -prefix
    0.07
    .abort
    0.07
     Spike
    0.07
    前三季度
    0.07
    Valor
    0.07
     mult
    0.07
     noen
    0.07
     surprised
    0.07
    습니다
    0.07
    Activations Density 0.123%

    No Known Activations