© 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. 96350
    Prev
    Next
    INDEX
    Explanations

    computer code and technical terms

    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
    ines
    -0.79
    ина
    -0.77
    ina
    -0.77
    inate
    -0.75
    ine
    -0.73
    inal
    -0.71
    inations
    -0.68
    ination
    -0.68
    iny
    -0.67
    INE
    -0.66
    POSITIVE LOGITS
    åĦĴ
    0.28
    ä¼´
    0.26
    æĸ¯
    0.26
    arov
    0.26
    -speaking
    0.26
    ARC
    0.25
    çºłç»ĵ
    0.25
    æ¯ĶåĪ©
    0.24
    icum
    0.24
    cies
    0.24
    Activations Density 0.983%

    No Known Activations