© 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. 39495
    Prev
    Next
    INDEX
    Explanations

    software licensing

    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
    ride
    -0.31
    rops
    -0.30
    rich
    -0.29
    ru
    -0.28
    rup
    -0.27
    rics
    -0.27
    indrome
    -0.27
    arith
    -0.26
    riz
    -0.26
    stüt
    -0.26
    POSITIVE LOGITS
    ved
    0.28
     Dante
    0.28
    ge
    0.28
    æħİ
    0.27
    vn
    0.26
     weakest
    0.26
    iect
    0.26
    常åĬ¡
    0.25
    cht
    0.24
     Trent
    0.24
    Activations Density 2.671%

    No Known Activations