© 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. 20-TRANSCODER-HP
    7. 130004
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åģĪ
    -0.26
     назнаÑĩен
    -0.25
    ä¸İåıijå±ķ
    -0.25
    lycer
    -0.25
    é£ĵ
    -0.25
     fret
    -0.24
     nic
    -0.24
    æĩĴ
    -0.24
    ×ŀף
    -0.24
    æ¨Ļ
    -0.23
    POSITIVE LOGITS
    ä»ĭ
    0.31
    è¿İæİ¥
    0.27
     stuff
    0.27
    æĭ·
    0.25
    ä»ħä¾ĽåıĤèĢĥ
    0.25
    _clock
    0.25
     sang
    0.24
    xFFFFFFFF
    0.24
     screwed
    0.24
    äºĨåĩºæĿ¥
    0.24
    Activations Density 9.624%

    No Known Activations