© 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. 30-TRANSCODER-HP
    7. 96430
    Prev
    Next
    INDEX
    Explanations

    Medical imaging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otte
    -0.30
    ABCDEFG
    -0.25
     puss
    -0.25
    èİ·å¾ĹæĦŁ
    -0.25
     Superior
    -0.25
    ÑģÑĤеÑĢ
    -0.25
     jose
    -0.24
    osis
    -0.24
    odel
    -0.24
     Advisors
    -0.24
    POSITIVE LOGITS
    lder
    0.29
    è·Łè¸ª
    0.28
    èŀºæĹĭ
    0.26
    ä¸į容
    0.26
    éĻįåĪ°
    0.26
     net
    0.24
     Hel
    0.24
    ims
    0.24
     subtree
    0.24
    led
    0.24
    Activations Density 0.885%

    No Known Activations