© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151213
    Prev
    Next
    INDEX
    Explanations

    medical treatments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     unique
    -0.33
     uniquely
    -0.32
    å¾ĭ
    -0.29
     Unique
    -0.27
     discriminate
    -0.27
     cond
    -0.26
     ste
    -0.26
    lem
    -0.26
     reim
    -0.26
    anz
    -0.25
    POSITIVE LOGITS
    ocurrency
    0.29
    locals
    0.28
    æīĵå¾Ĺ
    0.28
    icamente
    0.28
    uably
    0.27
    ipeg
    0.27
    icularly
    0.27
    stype
    0.26
    éĹªçĶµ
    0.26
     cheek
    0.25
    Activations Density 0.122%

    No Known Activations