© 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. 163812
    Prev
    Next
    INDEX
    Explanations

    )

    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
    çļĦä¸ĢéĿ¢
    -0.28
    çļĦ人
    -0.27
    åı¬
    -0.27
    à¨Ĩ
    -0.26
    lse
    -0.25
    çļĦçĪ±æĥħ
    -0.25
    çļĦæľĭåıĭ
    -0.25
    çĬĦ
    -0.25
    ä¸įè¿ľ
    -0.24
    alie
    -0.24
    POSITIVE LOGITS
    mittel
    0.27
    èIJĿ
    0.26
    di
    0.26
    nic
    0.25
     tide
    0.25
    -coded
    0.25
    èĢIJ
    0.25
    åĽ½åĨħå¤ĸ
    0.25
    ढ
    0.25
    -consuming
    0.24
    Activations Density 0.022%

    No Known Activations