© 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. 56961
    Prev
    Next
    INDEX
    Explanations

    Shapes and structures

    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
     remar
    -0.31
     replacements
    -0.29
    åĬ¨
    -0.27
    çī¹èī²
    -0.27
    rement
    -0.26
     exploit
    -0.26
    åĭķ
    -0.26
    markdown
    -0.25
    Activ
    -0.25
     replacement
    -0.25
    POSITIVE LOGITS
     aspiring
    0.28
    为ä¸ŃåĽ½
    0.28
    'n
    0.27
    ä¸ĢéŨ
    0.27
     fragment
    0.26
    ÙħÙĪس
    0.26
    æĪIJ为ä¸ĢåIJį
    0.25
    åİļåİļ
    0.25
    ä¸Ģ身
    0.25
     intermediate
    0.25
    Activations Density 0.002%

    No Known Activations