© 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. 27-TRANSCODER-HP
    7. 57402
    Prev
    Next
    INDEX
    Explanations

    pre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vore
    -0.29
     borderColor
    -0.27
    Q
    -0.27
    åŁºæľ¬åİŁåĪĻ
    -0.26
     pig
    -0.26
    æĽĿåħī
    -0.26
    aramel
    -0.25
    æĬĬæĮģ
    -0.24
    åħ¨éĿ¢æıIJåįĩ
    -0.24
     mı
    -0.24
    POSITIVE LOGITS
    wright
    0.26
    edriver
    0.26
    croft
    0.25
    ertino
    0.25
     WAV
    0.25
    åķĨä¸ļ
    0.25
    .SetActive
    0.25
     commercial
    0.25
    -columns
    0.24
    pany
    0.24
    Activations Density 0.005%

    No Known Activations