© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162061
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eric
    -0.31
    è¿ijåĩłå¹´
    -0.27
    æĹ¢
    -0.27
    æĢĿæĥ³
    -0.27
     today
    -0.26
    æľ¬æľŁ
    -0.26
    ä»ĬæĹ¥
    -0.26
    è¿ijå¹´æĿ¥
    -0.25
    è¿ijæľŁ
    -0.24
     FY
    -0.24
    POSITIVE LOGITS
    æŃ»äºĨ
    0.28
    ahead
    0.27
    æŃ»åİ»
    0.26
    dead
    0.26
    LOPT
    0.25
    ç»ĵæĿŁäºĨ
    0.25
     Chamber
    0.25
    设ç«ĭäºĨ
    0.25
    _portfolio
    0.24
    _reward
    0.24
    Activations Density 0.022%

    No Known Activations