© 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. 30-TRANSCODER-HP
    7. 95523
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ahead
    -1.00
     Ahead
    -0.87
    ahead
    -0.75
    Ahead
    -0.69
    -ahead
    -0.68
     behind
    -0.66
     Behind
    -0.61
    Behind
    -0.56
    åīį
    -0.50
     advance
    -0.48
    POSITIVE LOGITS
     catch
    0.30
    tex
    0.28
     catches
    0.27
    than
    0.27
     aug
    0.27
    pcf
    0.26
    Catch
    0.26
    uds
    0.25
    	catch
    0.24
    eba
    0.24
    Activations Density 0.897%

    No Known Activations