© 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. 163432
    Prev
    Next
    INDEX
    Explanations

    Speaker/profession

    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
    ç·´
    -0.27
    illac
    -0.26
    uels
    -0.25
    zug
    -0.25
    edException
    -0.24
    berman
    -0.24
     Stadium
    -0.24
    ita
    -0.24
    Ster
    -0.24
    ritten
    -0.24
    POSITIVE LOGITS
    /topics
    0.31
     prov
    0.29
     walks
    0.26
    .words
    0.25
    Forget
    0.25
     Cap
    0.25
     convention
    0.24
     cosm
    0.24
     himself
    0.24
     cap
    0.24
    Activations Density 0.005%

    No Known Activations