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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4929
    Prev
    Next
    INDEX
    Explanations

    trademarks, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłæīĢ
    -0.28
    åIJĦæł·
    -0.26
     approach
    -0.24
     speaker
    -0.24
    ");
    -0.23
     paycheck
    -0.23
    [sub
    -0.23
    èĪĴéĢĤ
    -0.23
     LGPL
    -0.22
    "N
    -0.22
    POSITIVE LOGITS
    hee
    0.27
    cur
    0.26
    eria
    0.26
    æľįåĬ¡åķĨ
    0.25
    biz
    0.25
    äºī夺
    0.25
    计éĩı
    0.24
    ä¹ŁéľĢè¦ģ
    0.24
     Inf
    0.24
    xee
    0.24
    Activations Density 0.011%

    No Known Activations