© 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. 30-TRANSCODER-HP
    7. 94907
    Prev
    Next
    INDEX
    Explanations

    board

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     staff
    -0.29
    rang
    -0.28
    èĴĻ
    -0.26
    æī¹
    -0.25
     cauliflower
    -0.25
    罩
    -0.25
    æİĮæı¡
    -0.25
    åĽ¢å§Ķ
    -0.25
    éķ¿
    -0.25
    Staff
    -0.25
    POSITIVE LOGITS
     recht
    0.29
    otes
    0.28
    verter
    0.28
    lights
    0.27
    ÙĦاÙĨ
    0.26
    çıŃ车
    0.25
    çģ«çĥ§
    0.24
     Comedy
    0.24
    -valid
    0.24
    edException
    0.24
    Activations Density 0.103%

    No Known Activations