© 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. 22691
    Prev
    Next
    INDEX
    Explanations

    Gu

    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
    keh
    -0.28
    opleft
    -0.27
    LayoutManager
    -0.27
    èĥĻ
    -0.26
    oldt
    -0.26
    ansa
    -0.25
    âĤĭ
    -0.25
    iline
    -0.25
    è¾ķ
    -0.25
    rade
    -0.25
    POSITIVE LOGITS
    ucci
    0.31
    äºĨ解
    0.26
     alle
    0.26
     combined
    0.26
    endor
    0.24
     combine
    0.24
     té
    0.24
    å¾Ĺ太
    0.24
    ãģĪãĤĭ
    0.24
    esc
    0.24
    Activations Density 0.485%

    No Known Activations