© 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. 9781
    Prev
    Next
    INDEX
    Explanations

    Code/Identifiers

    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
    ä¹Łä¸įåı¯èĥ½
    -0.26
    .Imp
    -0.25
    .br
    -0.25
     Implicit
    -0.25
    èĦ¸
    -0.24
    _bloc
    -0.24
    =cut
    -0.24
    é¢ī
    -0.24
     memcmp
    -0.24
    éģıåĪ¶
    -0.24
    POSITIVE LOGITS
    anz
    0.30
    Sim
    0.26
    ষ
    0.26
    èĭ¦
    0.26
     finder
    0.25
    ower
    0.25
    ...,
    0.25
    üst
    0.25
     Laurel
    0.25
    /content
    0.25
    Activations Density 0.002%

    No Known Activations