© 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. 162307
    Prev
    Next
    INDEX
    Explanations

    Code/math snippets

    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
    -sample
    -0.25
    avana
    -0.25
    éĽĨ
    -0.25
    HV
    -0.25
    morgan
    -0.25
    rou
    -0.24
    mate
    -0.24
    åĨ·éĿĻ
    -0.24
    ting
    -0.24
    s
    -0.24
    POSITIVE LOGITS
    çķĽ
    0.28
     affairs
    0.27
     Pew
    0.27
     animator
    0.26
     expelled
    0.25
     explosion
    0.25
    NCY
    0.24
     cryst
    0.24
     Barney
    0.24
    é¢ĦåijĬ
    0.24
    Activations Density 0.058%

    No Known Activations