© 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. 25-TRANSCODER-HP
    7. 107033
    Prev
    Next
    INDEX
    Explanations

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¼ĺåĮĸ
    -0.28
    æŁĶæĢ§
    -0.27
    rep
    -0.27
    æĶ¹åĸĦ
    -0.27
     optimize
    -0.26
    mayı
    -0.26
     cheering
    -0.26
     unintended
    -0.25
    estroy
    -0.25
     bene
    -0.25
    POSITIVE LOGITS
    æµĭ
    0.47
    accur
    0.44
    Accuracy
    0.42
     detecting
    0.42
    çĽijæµĭ
    0.41
     Accuracy
    0.41
     detection
    0.41
     accuracy
    0.41
    åĩĨç¡®æĢ§
    0.40
    æĻ®æŁ¥
    0.40
    Activations Density 0.933%

    No Known Activations