© 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. 33-TRANSCODER-HP
    7. 53192
    Prev
    Next
    INDEX
    Explanations

    medical physical therapy contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¾½
    -0.27
    Division
    -0.26
    æµıè§Ī
    -0.26
     practices
    -0.25
    èĪŀ
    -0.25
    èµŁ
    -0.25
    æ¼Ķç»ĥ
    -0.25
    MENTS
    -0.24
     practice
    -0.24
     Briggs
    -0.24
    POSITIVE LOGITS
    acle
    0.31
    .tie
    0.29
    ensible
    0.27
    oral
    0.27
    ENCH
    0.26
     kir
    0.26
    ersistent
    0.25
    sat
    0.25
    .appspot
    0.25
     Tight
    0.25
    Activations Density 0.016%

    No Known Activations