© 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. 110130
    Prev
    Next
    INDEX
    Explanations

    License

    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
    ök
    -0.07
    .handle
    -0.07
     Science
    -0.07
     esl
    -0.07
    ö
    -0.07
    aptor
    -0.07
    מיתי
    -0.07
     การ
    -0.06
     prepared
    -0.06
     Factor
    -0.06
    POSITIVE LOGITS
    brig
    0.07
    банк
    0.07
    保湿
    0.07
     مثل
    0.07
    家乡
    0.07
    ItemType
    0.07
    孩
    0.06
     hairstyle
    0.06
    :black
    0.06
    的颜色
    0.06
    Activations Density 0.002%

    No Known Activations