© 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. 42606
    Prev
    Next
    INDEX
    Explanations

    Computer code or art

    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
    erner
    -0.27
    asn
    -0.27
    asters
    -0.26
    oler
    -0.26
     около
    -0.25
    xCA
    -0.25
    à¹Īาย
    -0.24
    ije
    -0.24
    upa
    -0.24
    éŀį
    -0.24
    POSITIVE LOGITS
    iveness
    0.32
     organic
    0.30
    èĮ§
    0.29
     interpretation
    0.28
    æľīæľº
    0.28
    åĪĽéĢłåĬĽ
    0.27
     discovery
    0.27
    duino
    0.27
     curiosity
    0.27
     иÑģкÑĥÑģÑģÑĤв
    0.26
    Activations Density 0.000%

    No Known Activations