© 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. 33-TRANSCODER-HP
    7. 53842
    Prev
    Next
    INDEX
    Explanations

    Washington

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pollo
    -0.28
     knob
    -0.28
     Inner
    -0.26
     knobs
    -0.26
     voc
    -0.26
    ten
    -0.25
    kus
    -0.25
    .Inner
    -0.24
     findAll
    -0.24
    reten
    -0.24
    POSITIVE LOGITS
     UID
    0.28
    ulong
    0.28
    chia
    0.27
    из
    0.27
    ढ
    0.27
    .cid
    0.25
    AAD
    0.25
    åĽ½åĬ¡
    0.24
     cid
    0.24
    ader
    0.24
    Activations Density 0.002%

    No Known Activations