© 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. 27-TRANSCODER-HP
    7. 57549
    Prev
    Next
    INDEX
    Explanations

    medical research, drug targets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moo
    -0.28
    åİ¿å§Ķ书记
    -0.28
    éļĶ离
    -0.27
    æ°´æµģ
    -0.26
     scale
    -0.26
     itemCount
    -0.26
     globalization
    -0.25
     wall
    -0.25
     famously
    -0.24
    è¾¹çķĮ
    -0.24
    POSITIVE LOGITS
    æ»į
    0.27
    fällig
    0.27
    ä¿®
    0.26
    æĸ°å½¢åĬ¿ä¸ĭ
    0.26
    incip
    0.25
    modo
    0.24
    å¹´ä¸ĭåįĬå¹´
    0.24
    asso
    0.24
    ufs
    0.24
     Velvet
    0.24
    Activations Density 0.046%

    No Known Activations