© 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. 5379
    Prev
    Next
    INDEX
    Explanations

    static or private

    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
     możliwe
    -0.08
     dripping
    -0.07
    퓖
    -0.07
     _,
    -0.07
    농
    -0.07
     rv
    -0.06
    .new
    -0.06
    рг
    -0.06
     totalPages
    -0.06
    --------↵
    -0.06
    POSITIVE LOGITS
     Charter
    0.07
    קידום
    0.07
     programmes
    0.07
    抗衡
    0.07
    Ⲁ
    0.07
    كاميرا
    0.07
    -most
    0.07
    事件
    0.07
     subsidies
    0.07
    半年
    0.07
    Activations Density 0.021%

    No Known Activations