© 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. 23-TRANSCODER-HP
    7. 24281
    Prev
    Next
    INDEX
    Explanations

    quickly, easily, easy

    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
    èµ°ä¸ĭåİ»
    -0.28
    å±ŀå®ŀ
    -0.28
    èĢĮæĪIJ
    -0.27
     Rising
    -0.27
    æĬ¥åºŁ
    -0.26
    ç»ĵ
    -0.25
    éĥ½åĸľæ¬¢
    -0.25
    psc
    -0.25
    å®Įæ¯ķ
    -0.25
    Pat
    -0.24
    POSITIVE LOGITS
     determination
    0.30
    -thumbnails
    0.29
    étr
    0.27
    åıĪèĥ½
    0.25
    èį»
    0.25
    ilies
    0.24
    hetics
    0.24
    etermination
    0.24
    ÑĤелÑĮнÑĭй
    0.24
    AndView
    0.24
    Activations Density 0.010%

    No Known Activations