© 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. 162626
    Prev
    Next
    INDEX
    Explanations

    plant

    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
    paced
    -0.28
    keit
    -0.27
    ãĥ³
    -0.26
    讲课
    -0.25
    s
    -0.24
    æĤŁ
    -0.24
    apsible
    -0.24
    vette
    -0.24
    &action
    -0.23
    sit
    -0.23
    POSITIVE LOGITS
    ç¿Ģ
    0.26
    禾
    0.26
     Wars
    0.25
    loo
    0.25
    oton
    0.24
    alog
    0.24
    atee
    0.24
    æĿī
    0.23
    boy
    0.23
    åĪĨè¡Į
    0.23
    Activations Density 0.028%

    No Known Activations