© 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. 53131
    Prev
    Next
    INDEX
    Explanations

    Fibrillation, medical topics

    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
    åħħ
    -0.30
    æ¯Ĵ
    -0.28
    åĢ¾
    -0.28
    ä½ĵåĨħ
    -0.26
    éĥ¨éĺŁ
    -0.26
    stell
    -0.25
    t
    -0.24
     eÄŁ
    -0.24
    ä½ĵ
    -0.24
    okin
    -0.24
    POSITIVE LOGITS
    ibs
    0.32
    ibri
    0.31
    ibrate
    0.30
    åĨįæĿ¥
    0.29
    inand
    0.29
    icals
    0.29
    ibil
    0.29
    inar
    0.28
    ina
    0.28
    inct
    0.28
    Activations Density 0.013%

    No Known Activations