© 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. 57202
    Prev
    Next
    INDEX
    Explanations

    increased

    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
    åĿĩåı¯
    -0.31
    é¢Ŀå¤ĸ
    -0.30
    åĻ¨
    -0.29
    便åı¯
    -0.28
    (extra
    -0.28
    lex
    -0.28
    çī¹æ®Ĭ
    -0.28
    çī¹æ®ĬçļĦ
    -0.28
    å®Įåħ¨åı¯ä»¥
    -0.28
    åĴĮå¹³
    -0.27
    POSITIVE LOGITS
    缺å¸Ń
    0.30
    èħIJè´¥
    0.29
    ippy
    0.28
    rosis
    0.27
    æģIJ
    0.26
    icky
    0.26
    说å®ŀ
    0.26
    æ£ł
    0.26
     fruition
    0.26
    è·Į
    0.25
    Activations Density 0.009%

    No Known Activations