© 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. 20-TRANSCODER-HP
    7. 107485
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Recorder
    -0.31
    akers
    -0.26
    姹
    -0.25
    REMOVE
    -0.25
    edReader
    -0.24
    emoth
    -0.24
    æ¦ľ
    -0.24
    une
    -0.24
    ellij
    -0.23
     grooming
    -0.23
    POSITIVE LOGITS
    èĩªè§ī
    0.26
    adients
    0.26
    soc
    0.26
    uya
    0.25
     vin
    0.24
    beits
    0.24
    æĢ»éĺŁ
    0.24
    Sig
    0.23
    antasy
    0.23
    绸
    0.23
    Activations Density 12.779%

    No Known Activations