© 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. 5948
    Prev
    Next
    INDEX
    Explanations

    Documentation and version numbers

    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
     independents
    -0.33
     setObject
    -0.29
     Independ
    -0.28
     Independent
    -0.28
    -available
    -0.27
    DEV
    -0.27
    ammer
    -0.25
     incons
    -0.25
    etten
    -0.25
    avail
    -0.25
    POSITIVE LOGITS
    ạ
    0.31
     bin
    0.30
    ä¸īå¹´
    0.28
    ISTA
    0.27
    两年
    0.26
    venth
    0.26
    ién
    0.26
    两年åīį
    0.26
    istas
    0.26
    轨
    0.26
    Activations Density 0.004%

    No Known Activations