© 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. 163832
    Prev
    Next
    INDEX
    Explanations

    code/numerical output

    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
    gang
    -0.27
    æİĴè¡Į
    -0.25
    endregion
    -0.25
    eling
    -0.25
     declaring
    -0.24
     considering
    -0.24
    nels
    -0.24
     bach
    -0.24
     chá»īnh
    -0.23
    åĪĹåħ¥
    -0.23
    POSITIVE LOGITS
    åħľ
    0.27
    _inline
    0.26
     corpor
    0.25
    urope
    0.25
    ser
    0.25
    -highlight
    0.25
    æĵį
    0.24
    udos
    0.24
    ayer
    0.24
    kea
    0.24
    Activations Density 0.113%

    No Known Activations