© 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. 57016
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
     heaven
    -0.44
    æıĴåħ¥
    -0.40
     insert
    -0.39
    Insert
    -0.38
    insert
    -0.38
     INSERT
    -0.36
    INSERT
    -0.35
     Insert
    -0.35
     insertion
    -0.35
    $insert
    -0.35
    POSITIVE LOGITS
    ç»ĵ
    0.26
    acco
    0.25
    äºļ
    0.25
     RADIO
    0.25
    lc
    0.24
    çıŀ
    0.24
    обоÑĢ
    0.24
     RENDER
    0.24
    qs
    0.23
    åĤ¨å¤ĩ
    0.23
    Activations Density 0.007%

    No Known Activations