© 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. 12-TRANSCODER-HP
    7. 22711
    Prev
    Next
    INDEX
    Explanations

    ovarian cancer and other cancers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŃĶ
    -0.32
    åĽŀçŃĶ
    -0.27
    fsp
    -0.27
     extended
    -0.27
     contact
    -0.27
    ote
    -0.26
     touch
    -0.26
    NC
    -0.26
    éĢ®
    -0.26
    _extended
    -0.25
    POSITIVE LOGITS
    ActivityCreated
    0.27
    åĶĩ
    0.26
    ç»ıæµİæĬĢæľ¯
    0.26
    cripcion
    0.25
    ç§ijæĬĢèĤ¡ä»½
    0.25
    åĩłæŃ¥
    0.24
    ç§ijæĬĢæĪIJæŀľ
    0.24
    creen
    0.24
    äºĨåIJ§
    0.24
    äºĨåĩºæĿ¥
    0.24
    Activations Density 0.002%

    No Known Activations