© 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. 43709
    Prev
    Next
    INDEX
    Explanations

    Air Force/aviation

    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
    Ascii
    -0.29
     antis
    -0.26
    compound
    -0.25
    asa
    -0.24
    éĩį
    -0.24
     Treasure
    -0.24
    antis
    -0.24
     дек
    -0.24
     mer
    -0.23
     compound
    -0.23
    POSITIVE LOGITS
    ãĤ±ãĥĥãĥĪ
    0.29
    ç¼ĺ
    0.27
    ei
    0.26
    uous
    0.26
    ifton
    0.25
     sublic
    0.25
    Wo
    0.24
    ÑĥÑī
    0.24
    quam
    0.24
    uem
    0.24
    Activations Density 0.002%

    No Known Activations