© 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. 57232
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    æľīè¿ĩ
    -0.26
    M
    -0.25
    é¢Ħå¤ĩ
    -0.24
     M
    -0.24
    Cour
    -0.24
     movement
    -0.23
    aversal
    -0.23
     clever
    -0.23
     Pour
    -0.23
     somehow
    -0.23
    POSITIVE LOGITS
    amax
    0.28
    éľīç´ł
    0.26
    axy
    0.26
     Baghd
    0.24
    åŃĽ
    0.24
    ulkan
    0.23
     lighten
    0.23
    æ®Ħ
    0.23
    ittel
    0.23
    itez
    0.23
    Activations Density 1.170%

    No Known Activations