© 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. 7676
    Prev
    Next
    INDEX
    Explanations

    After

    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
     after
    -0.32
     Wait
    -0.31
    Wait
    -0.30
    çŃīå¾ħ
    -0.30
    Loader
    -0.29
     wait
    -0.28
    ä¹ĭåIJİ
    -0.28
     After
    -0.28
    åIJİ
    -0.28
     later
    -0.28
    POSITIVE LOGITS
    æŁ¥æĺİ
    0.29
     finishing
    0.27
    wards
    0.26
     оÑģÑĥÑīеÑģÑĤв
    0.26
    odia
    0.26
     Identified
    0.25
    çIJĨ解åĴĮ
    0.25
    Cancelled
    0.25
    -reviewed
    0.24
    dehyde
    0.24
    Activations Density 0.010%

    No Known Activations