© 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. 57349
    Prev
    Next
    INDEX
    Explanations

    Calculation

    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
     medida
    -0.28
    æµĭè¯ķ
    -0.28
     measured
    -0.28
    æµĭéĩı
    -0.27
     measuring
    -0.26
     Museum
    -0.26
     mesure
    -0.25
    è¯ķéªĮ
    -0.25
    odos
    -0.25
    ä¹Ļæĸ¹
    -0.25
    POSITIVE LOGITS
     calculation
    0.61
    计ç®Ĺ
    0.60
     calculations
    0.60
    æķ°æį®åĪĨæŀIJ
    0.55
     Calculation
    0.53
    ç®Ĺæ³ķ
    0.52
    åĪĨæŀIJ
    0.52
    ç®Ĺ
    0.52
     analysis
    0.51
    è¨Īç®Ĺ
    0.50
    Activations Density 0.006%

    No Known Activations