© 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. 141637
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
     executed
    -0.32
    ç»Łè®¡æķ°æį®
    -0.27
    æī§è¡Į
    -0.27
    uffled
    -0.26
     randomly
    -0.26
    åŁ¹è®ŃæľºæŀĦ
    -0.26
     snapped
    -0.25
     Plus
    -0.25
     —↵↵
    -0.25
    ä»»
    -0.25
    POSITIVE LOGITS
    rev
    0.25
     amendment
    0.25
     remot
    0.25
    eq
    0.25
    ä¹ĭæĥħ
    0.24
    æĥ³è¿ĩ
    0.24
    tel
    0.23
     paragraph
    0.23
    æĿ¡è§Ħå®ļ
    0.23
    _sentence
    0.23
    Activations Density 68.595%

    No Known Activations