© 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. 162382
    Prev
    Next
    INDEX
    Explanations

    software, code

    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
    кал
    -0.30
    æĭĬ
    -0.28
    son
    -0.27
    笺
    -0.27
     Structure
    -0.26
     fragments
    -0.25
    èijĹ
    -0.25
    .structure
    -0.25
    kre
    -0.23
    Family
    -0.23
    POSITIVE LOGITS
     timing
    0.31
    åľ¨åħ¶
    0.27
     initial
    0.27
     Mana
    0.27
    timing
    0.26
     Timing
    0.26
    æŀ¢
    0.26
    Timing
    0.26
    _timing
    0.25
    initial
    0.24
    Activations Density 0.005%

    No Known Activations