© 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. 25-TRANSCODER-HP
    7. 107934
    Prev
    Next
    INDEX
    Explanations

    Online access or search

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ«
    -0.28
    ersed
    -0.27
    eway
    -0.26
    ITO
    -0.25
    æĮģãģ£ãģ¦
    -0.23
    ardo
    -0.23
    aret
    -0.23
    ITT
    -0.23
    ä»İ
    -0.23
    esion
    -0.23
    POSITIVE LOGITS
    继ç»Ńä¿ĿæĮģ
    0.27
     haze
    0.26
    äºĨè§£æĽ´å¤ļ
    0.25
    å±ħ室
    0.25
    itur
    0.25
    coder
    0.25
    cope
    0.25
    åIJİæİĴ
    0.25
    éĩįçĤ¹é¢ĨåŁŁ
    0.24
    â½°
    0.24
    Activations Density 0.119%

    No Known Activations