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. 2822
    Prev
    Next
    INDEX
    Explanations

    M

    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
    歌曲
    -0.07
     silent
    -0.07
     illum
    -0.07
     conceive
    -0.07
     online
    -0.07
     Legends
    -0.07
     Date
    -0.07
    เน
    -0.07
     delegate
    -0.06
    .edu
    -0.06
    POSITIVE LOGITS
     the
    0.09
    M
    0.08
     and
    0.08
     mais
    0.07
     거의
    0.07
    m
    0.07
     M
    0.07
    .route
    0.07
    מוס
    0.06
     más
    0.06
    Activations Density 0.927%

    No Known Activations