© 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. 23404
    Prev
    Next
    INDEX
    Explanations

    worse

    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
    bable
    -0.30
    çļĦåķĨåĵģ
    -0.27
     sym
    -0.25
    hil
    -0.24
    çļĦåĵģçīĮ
    -0.24
    çļĦè·Ŀ离
    -0.24
    æı¡
    -0.24
    kehr
    -0.24
    çļĦæ¯ĶèµĽ
    -0.23
    วล
    -0.23
    POSITIVE LOGITS
    èĥĻ
    0.28
    apes
    0.25
    proved
    0.25
     dev
    0.25
     sails
    0.24
    abwe
    0.24
    алÑĮнÑĭм
    0.24
    paren
    0.24
     ze
    0.23
    experiment
    0.23
    Activations Density 0.003%

    No Known Activations