© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149171
    Prev
    Next
    INDEX
    Explanations

    Long or Short

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    istration
    -0.27
    ä¸Ģå¼Ģå§ĭå°±
    -0.25
    office
    -0.25
    åħ·ä½ĵçļĦ
    -0.25
    okers
    -0.25
    ä¸Ģ个æĸ°çļĦ
    -0.24
     purposely
    -0.24
    Ñĥг
    -0.23
    lesia
    -0.23
    usta
    -0.23
    POSITIVE LOGITS
    quoi
    0.27
    elow
    0.26
    éĤ£å¤©
    0.25
    erner
    0.25
    Finally
    0.25
    Manchester
    0.24
    al
    0.24
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.24
    illy
    0.23
     Finally
    0.23
    Activations Density 0.182%

    No Known Activations