© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8871
    Prev
    Next
    INDEX
    Explanations

    Answering questions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦçŃĶæ¡Ī
    -0.35
    çŃĶãģĪ
    -0.32
    -answer
    -0.31
    çŃĶæ¡Ī
    -0.31
    çļĦåĽŀçŃĶ
    -0.29
    _answer
    -0.29
    Answer
    -0.29
     ëĭµ
    -0.28
    ä¸ĩåįĥ
    -0.28
     answer
    -0.27
    POSITIVE LOGITS
    åIJ¸å¼ķæĽ´å¤ļ
    0.26
     surprising
    0.24
    hal
    0.24
    =('
    0.24
    ีย
    0.23
     elective
    0.23
    çĤ¹æ»´
    0.23
     generous
    0.23
    vers
    0.23
    psz
    0.23
    Activations Density 0.000%

    No Known Activations