© 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. 57542
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Åŀa
    -0.29
    isma
    -0.28
    OLID
    -0.26
     CSA
    -0.26
    caa
    -0.25
     entitled
    -0.24
    çļĦæŃ¥ä¼IJ
    -0.24
    ľ
    -0.24
    ana
    -0.24
    ibe
    -0.23
    POSITIVE LOGITS
    esty
    0.30
    atron
    0.28
    resse
    0.28
     pand
    0.25
    oron
    0.25
    åŁĶ
    0.24
    è¹Ĭ
    0.24
    ä½ıåľ¨
    0.23
     اÙĦÙħÙĪجÙĪد
    0.23
    å¯Ħ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.