© 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. 163517
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    æĹłæīĢè°ĵ
    -0.30
    sed
    -0.29
    请æĤ¨
    -0.27
    sus
    -0.26
    ansom
    -0.26
    laces
    -0.26
    ål
    -0.26
    ieder
    -0.26
    sav
    -0.26
    dì
    -0.25
    POSITIVE LOGITS
    itude
    0.34
    ity
    0.27
    onga
    0.27
    ness
    0.26
    NESS
    0.25
     McDon
    0.25
     tonnes
    0.24
    ilan
    0.24
    ó
    0.23
    çŃĭ
    0.23
    Activations Density 0.104%

    No Known Activations