© 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. 33-TRANSCODER-HP
    7. 54254
    Prev
    Next
    INDEX
    Explanations

    ex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exploring
    -0.36
     explored
    -0.35
     explore
    -0.35
     exploration
    -0.34
     explores
    -0.31
     Exploration
    -0.29
     investigate
    -0.29
     examination
    -0.29
     studying
    -0.28
     analyzed
    -0.28
    POSITIVE LOGITS
     Ex
    1.02
    ex
    0.97
     ex
    0.96
    Ex
    0.91
    .ex
    0.75
    _ex
    0.75
    -ex
    0.74
    ’ex
    0.69
    'ex
    0.68
    (ex
    0.65
    Activations Density 0.024%

    No Known Activations