© 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. 42593
    Prev
    Next
    INDEX
    Explanations

    hor

    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
    utr
    -0.27
    fre
    -0.27
    æĨĭ
    -0.27
    lesi
    -0.25
     hist
    -0.25
    ãĥĴ
    -0.25
    å©Ĩ
    -0.25
    pector
    -0.25
    ht
    -0.25
    ore
    -0.24
    POSITIVE LOGITS
    izo
    0.30
    izons
    0.29
    æºī
    0.28
    iz
    0.28
    æľĹ
    0.26
     Bid
    0.25
    WARD
    0.25
    ional
    0.25
    Ont
    0.25
    izon
    0.24
    Activations Density 0.001%

    No Known Activations