© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23848
    Prev
    Next
    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DET
    -0.28
    iento
    -0.27
    mdi
    -0.26
    å®ī举
    -0.26
    SCRI
    -0.26
    ERV
    -0.26
     Kahn
    -0.25
     interp
    -0.25
     Sutton
    -0.25
     Accord
    -0.24
    POSITIVE LOGITS
    inski
    0.27
    igital
    0.27
    ä¼į
    0.25
     trusted
    0.24
    ç»ĵ
    0.24
     ranged
    0.24
    emphasis
    0.24
    ä¿¡ä»»
    0.24
    allah
    0.24
    itel
    0.23
    Activations Density 0.153%

    No Known Activations