© 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. 43044
    Prev
    Next
    INDEX
    Explanations

    medical, biological topics

    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
     Se
    -0.29
    ãĥīãĥ©
    -0.29
    callable
    -0.25
    urger
    -0.25
    aret
    -0.25
    éĿĴ
    -0.24
    _pins
    -0.24
    æĩ
    -0.24
     se
    -0.23
    DAT
    -0.23
    POSITIVE LOGITS
    STM
    0.26
    éĤĤ
    0.26
    odor
    0.25
    fec
    0.24
    surname
    0.24
    ä¾
    0.24
     rehearsal
    0.24
    ÙĬÙħØ©
    0.24
    IQ
    0.24
     repetition
    0.24
    Activations Density 0.003%

    No Known Activations