© 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. 7769
    Prev
    Next
    INDEX
    Explanations

    Negative situations/turning points

    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
     submits
    -0.29
    ãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    -0.29
    /cpp
    -0.27
    滥çĶ¨
    -0.26
     reusable
    -0.26
     <$
    -0.25
    ваÑĤÑĮ
    -0.25
     quits
    -0.25
    qus
    -0.25
    даеÑĤÑģÑı
    -0.25
    POSITIVE LOGITS
     took
    0.36
     was
    0.35
     resulted
    0.33
    å¼ķèµ·äºĨ
    0.33
     led
    0.33
    èµ·äºĨ
    0.32
     began
    0.32
     vanished
    0.31
    产çĶŁäºĨ
    0.31
     wasn
    0.31
    Activations Density 0.002%

    No Known Activations