© 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. 39856
    Prev
    Next
    INDEX
    Explanations

    grapes and related topics

    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
    ship
    -0.31
    nya
    -0.30
    ness
    -0.28
    ships
    -0.27
    thes
    -0.27
    ll
    -0.26
    许
    -0.26
    ns
    -0.26
     vin
    -0.26
    ly
    -0.25
    POSITIVE LOGITS
    gars
    0.42
    g
    0.41
    gar
    0.40
    gis
    0.37
    gage
    0.37
    ga
    0.37
    gro
    0.37
    gard
    0.37
    gx
    0.37
    gas
    0.36
    Activations Density 0.318%

    No Known Activations