© 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. 162679
    Prev
    Next
    INDEX
    Explanations

    starch

    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
    CRT
    -0.25
    åĵĹ
    -0.25
    ivas
    -0.25
    iji
    -0.25
    CRM
    -0.25
    iams
    -0.24
    jamin
    -0.24
    Ñİ
    -0.24
    omy
    -0.24
    imity
    -0.24
    POSITIVE LOGITS
    s
    0.30
    ernes
    0.28
    ËĬ
    0.28
    .openConnection
    0.27
    _/
    0.26
    åĴ¸
    0.24
    ︶
    0.24
    ︵
    0.24
    âģ½
    0.24
     Lone
    0.23
    Activations Density 0.028%

    No Known Activations