© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40446
    Prev
    Next
    INDEX
    Explanations

    sol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lens
    -0.30
    -flash
    -0.27
    -www
    -0.26
    аÑģÑģ
    -0.26
     IHttp
    -0.26
    -heart
    -0.25
     Ending
    -0.25
    FLASH
    -0.25
     Hubbard
    -0.24
     Ingen
    -0.24
    POSITIVE LOGITS
    agna
    0.29
    强è¡Į
    0.28
    ä¼ģåĽ¾
    0.27
    anal
    0.25
    lac
    0.25
    æĿ¾å¼Ľ
    0.24
     forms
    0.24
    é¡¹çĽ®çļĦ
    0.24
    åıijå±ķä¸Ń
    0.24
     displays
    0.24
    Activations Density 30.610%

    No Known Activations