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. 2674
    Prev
    Next
    INDEX
    Explanations

    help

    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
    per
    -0.08
    dia
    -0.08
    xA
    -0.07
    SPA
    -0.07
    כח
    -0.07
     palabra
    -0.07
    美味し
    -0.07
     Ther
    -0.07
     charm
    -0.07
     bras
    -0.07
    POSITIVE LOGITS
     שלה
    0.08
    МИ
    0.08
     يعني
    0.07
    .XtraLayout
    0.07
    옮
    0.07
    .ComponentResourceManager
    0.07
    这个名字
    0.07
    指标
    0.07
    ציר
    0.07
     לצ
    0.07
    Activations Density 0.031%

    No Known Activations