© 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. 163118
    Prev
    Next
    INDEX
    Explanations

    recognize

    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
    æĦıåĽ¾
    -0.30
    spo
    -0.26
    Interested
    -0.26
     Maid
    -0.25
    apache
    -0.25
    Conf
    -0.25
    aran
    -0.25
     tert
    -0.25
    大å®Ĺ
    -0.24
     vũ
    -0.24
    POSITIVE LOGITS
    imore
    0.29
     that
    0.28
    emen
    0.28
    eur
    0.28
    ä¸Ģçľ¼
    0.26
    indr
    0.26
    assen
    0.26
    <hr
    0.26
     modular
    0.25
    istence
    0.25
    Activations Density 0.012%

    No Known Activations