© 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. 32-TRANSCODER-HP
    7. 42375
    Prev
    Next
    INDEX
    Explanations

    countries and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leh
    -0.27
     Area
    -0.27
    AREA
    -0.26
     AREA
    -0.25
     mirrors
    -0.24
    endir
    -0.24
    å°±è¿ŀ
    -0.24
     BOTH
    -0.24
     Left
    -0.24
     area
    -0.24
    POSITIVE LOGITS
     close
    0.49
     well
    0.47
    close
    0.43
    well
    0.42
     Close
    0.41
    Close
    0.40
     Well
    0.38
     closer
    0.38
    Well
    0.37
    _close
    0.37
    Activations Density 0.001%

    No Known Activations