© 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. 23-TRANSCODER-HP
    7. 162399
    Prev
    Next
    INDEX
    Explanations

    Code and technical jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rive
    -0.29
    wise
    -0.28
    <!--[
    -0.28
    icular
    -0.26
    ied
    -0.26
     türlü
    -0.25
    Ãłnh
    -0.25
    Å¡ÃŃ
    -0.25
    logue
    -0.24
    èĢĮå·²
    -0.24
    POSITIVE LOGITS
    举
    0.29
    èĪī
    0.27
    eah
    0.27
    alers
    0.26
    .um
    0.26
     But
    0.25
     collegiate
    0.25
    èĥ¸åīį
    0.25
     spont
    0.24
    _BC
    0.24
    Activations Density 0.165%

    No Known Activations