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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5972
    Prev
    Next
    INDEX
    Explanations

    Museums and collections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     addCriterion
    -0.30
    ilden
    -0.27
    _nc
    -0.27
    ollah
    -0.26
    nin
    -0.26
    (cin
    -0.26
    renal
    -0.25
    -exclusive
    -0.25
    请æĤ¨
    -0.25
    .qq
    -0.25
    POSITIVE LOGITS
    oreach
    0.25
    xies
    0.24
     mest
    0.24
    èĬ
    0.24
    _SAMPLES
    0.24
    ëŁī
    0.24
     chopping
    0.23
     mau
    0.23
    MJ
    0.23
    intros
    0.23
    Activations Density 0.013%

    No Known Activations