Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 130997
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    估值
    -0.07
     vũ
    -0.07
    _FOR
    -0.07
    你喜欢
    -0.07
     fout
    -0.07
    孕
    -0.07
     לפתוח
    -0.06
    ถาม
    -0.06
    治疗
    -0.06
    违法犯罪
    -0.06
    POSITIVE LOGITS
     обеспеч
    0.08
    海上
    0.08
     качестве
    0.07
     Хотя
    0.07
    .jboss
    0.07
    ystems
    0.07
     Particularly
    0.07
    ecessarily
    0.07
    _component
    0.07
     societies
    0.07
    Activations Density 0.008%

    No Known Activations