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. 130935
    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
    ừ
    -0.07
     hjem
    -0.07
    搜狐
    -0.07
    ᗢ
    -0.07
     chụp
    -0.06
    ㎞
    -0.06
    没问题
    -0.06
     leans
    -0.06
    _mux
    -0.06
     pretending
    -0.06
    POSITIVE LOGITS
    hythm
    0.07
     Voice
    0.07
    iosk
    0.07
     $(
    0.07
    后台
    0.07
    Courses
    0.07
     Core
    0.07
    Router
    0.06
     displays
    0.06
     frustrated
    0.06
    Activations Density 0.003%

    No Known Activations