© 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. 8704
    Prev
    Next
    INDEX
    Explanations

    automation

    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
    UTH
    -0.32
    ória
    -0.26
    licas
    -0.26
    embro
    -0.25
     dib
    -0.25
    mina
    -0.25
     sinon
    -0.24
    è®Ńç»ĥ
    -0.24
     fellowship
    -0.24
    ä¿Ŀå®Ī
    -0.24
    POSITIVE LOGITS
    èĩªåĬ¨
    0.75
     automatic
    0.75
     automated
    0.73
     automatically
    0.72
    automatic
    0.66
    èĩªåĭķ
    0.65
     авÑĤомаÑĤ
    0.63
     Automatic
    0.61
     automat
    0.61
    èĩªåĬ¨åĮĸ
    0.60
    Activations Density 0.001%

    No Known Activations