© 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. 22-TRANSCODER-HP
    7. 129561
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igli
    -0.31
    ergarten
    -0.30
     incoming
    -0.28
    ikal
    -0.27
    Incoming
    -0.26
     PolÃŃtica
    -0.26
    åºij
    -0.26
     Incoming
    -0.26
    mailer
    -0.25
    iple
    -0.25
    POSITIVE LOGITS
    çijķ
    0.25
    mit
    0.25
    çĶ±ä¸ŃåĽ½
    0.25
    itor
    0.24
    “
    0.24
    æĢ»ä½ĵ
    0.24
    âĺº
    0.24
    bra
    0.23
     cyn
    0.23
    ä¸Ģçīĩ
    0.23
    Activations Density 0.009%

    No Known Activations