© 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. 27-TRANSCODER-HP
    7. 7677
    Prev
    Next
    INDEX
    Explanations

    find

    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
    Negative Logits
    riet
    -0.27
    çļĦæĸ¹æ³ķ
    -0.26
    ri
    -0.25
    ilet
    -0.25
    çļĦä¸Ģ个
    -0.24
    agment
    -0.24
     Manus
    -0.24
    çļĦæľįåĬ¡
    -0.23
    tet
    -0.23
    æĹłè®ºæĺ¯
    -0.23
    POSITIVE LOGITS
     are
    0.57
    are
    0.56
    éĥ½éĿŀ常
    0.55
    éĥ½æĺ¯éĿŀ常
    0.54
    _are
    0.54
    .are
    0.53
    éĥ½æĺ¯
    0.53
    åĿĩ为
    0.52
    åĿĩ
    0.52
    éĥ½å¾Ī
    0.51
    Activations Density 0.001%

    No Known Activations