© 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. 25-TRANSCODER-HP
    7. 107224
    Prev
    Next
    INDEX
    Explanations

    Asthma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apol
    -0.29
    orra
    -0.29
    /vnd
    -0.26
    åħ¨æĿij
    -0.25
    venient
    -0.25
     accom
    -0.25
    æĿijæĿijæ°ij
    -0.24
     rational
    -0.23
    ially
    -0.23
    Ymd
    -0.23
    POSITIVE LOGITS
    azine
    0.29
    otonin
    0.29
    undo
    0.28
    æĮģä¹ħ
    0.27
    unde
    0.27
     Society
    0.27
    ight
    0.26
    ouri
    0.26
    dea
    0.25
    hton
    0.25
    Activations Density 1.011%

    No Known Activations