© 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. 162513
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    客è¿IJ
    -0.25
    queries
    -0.25
    éĥ¢
    -0.24
     Pháp
    -0.24
    ore
    -0.24
    _gem
    -0.24
    åŃĶ
    -0.24
    姻
    -0.23
    .constructor
    -0.23
    жи
    -0.23
    POSITIVE LOGITS
    uity
    0.31
     reveals
    0.27
    cling
    0.27
    å§Ķç»Ħç»ĩ
    0.27
    缸åħ³è§Ħå®ļ
    0.26
    atement
    0.26
    åİŁæłĩé¢ĺ
    0.24
    astically
    0.24
    atics
    0.24
    éĢıéľ²
    0.24
    Activations Density 0.007%

    No Known Activations