© 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. 56593
    Prev
    Next
    INDEX
    Explanations

    global problems

    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
    æ¡¡
    -0.30
    azines
    -0.30
    好å¥ĩ
    -0.29
    çIJ¯
    -0.27
     bure
    -0.26
    æīĢæľī
    -0.25
     bât
    -0.25
    rix
    -0.25
    ustom
    -0.25
     VIR
    -0.25
    POSITIVE LOGITS
    çªģåĩºéĹ®é¢ĺ
    0.30
    åħ¨çIJĥ
    0.30
    .INSTANCE
    0.28
     global
    0.28
    åĽ°
    0.28
    éĹ®é¢ĺæĺ¯
    0.27
    æ¶Ī失
    0.26
     problems
    0.25
     palm
    0.25
    åĽ½åĨħå¤ĸ
    0.25
    Activations Density 0.002%

    No Known Activations