© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39652
    Prev
    Next
    INDEX
    Explanations

    Companies and organizations

    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
     companies
    -0.82
     Companies
    -0.65
     company
    -0.61
     schools
    -0.61
    companies
    -0.60
    åħ¬åı¸
    -0.60
    éĻ¢æł¡
    -0.59
     businesses
    -0.58
     organizations
    -0.58
     firms
    -0.56
    POSITIVE LOGITS
    OMPI
    0.29
     parcel
    0.26
     legis
    0.25
     Trustees
    0.25
    _msgs
    0.24
    æĶ»çķ¥
    0.24
    ä¸Ģå°ģä¿¡
    0.24
    æīĺè¿IJ
    0.24
     mote
    0.24
    æĸ°ä¸ī
    0.24
    Activations Density 34.373%

    No Known Activations