© 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. 163369
    Prev
    Next
    INDEX
    Explanations

    Programming libraries and text

    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
    åĵįåºĶ
    -0.25
    fw
    -0.25
     organised
    -0.25
    ç©¿
    -0.25
    response
    -0.25
     convergence
    -0.24
    ä¸ŃæľŁ
    -0.24
    æ¹ĵ
    -0.24
     Wash
    -0.24
    è§Ĵ度
    -0.24
    POSITIVE LOGITS
    ktop
    0.29
     liners
    0.28
    Pieces
    0.27
    andom
    0.27
     liner
    0.26
    piece
    0.26
    pieces
    0.26
    ä¸ļ
    0.25
    LIN
    0.25
    .crt
    0.25
    Activations Density 0.001%

    No Known Activations