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

    Neuronpedia

    APICircuit 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. 2642
    Prev
    Next
    INDEX
    Explanations

    Legal code and reports

    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
     dik
    -0.08
     nguyên
    -0.07
    يس
    -0.07
    Entries
    -0.07
     YM
    -0.06
     kicks
    -0.06
     été
    -0.06
    מן
    -0.06
    ezier
    -0.06
     stata
    -0.06
    POSITIVE LOGITS
    (platform
    0.07
    童话
    0.07
    ATERIAL
    0.07
     {'
    0.06
     {"
    0.06
     grandfather
    0.06
    듐
    0.06
    ◈
    0.06
     bush
    0.06
     calculator
    0.06
    Activations Density 0.052%

    No Known Activations