© 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. 9332
    Prev
    Next
    INDEX
    Explanations

    compass directions

    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
    hurst
    -0.28
    imated
    -0.27
    aceut
    -0.27
    RELATED
    -0.26
     meld
    -0.26
     thematic
    -0.25
     spare
    -0.25
    etypes
    -0.25
    etically
    -0.25
    ç»İ
    -0.25
    POSITIVE LOGITS
    ä¸ĭ游
    0.28
    ven
    0.26
     mich
    0.25
    ccb
    0.25
    å½»åºķ
    0.24
    isen
    0.24
    åįĹæµ·
    0.24
    æĥ³å¿µ
    0.24
    lib
    0.24
    .Big
    0.24
    Activations Density 0.009%

    No Known Activations