© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41182
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨ä¸Ģ个
    -0.34
    çĶļèĩ³
    -0.28
    åľ¨åħ¶
    -0.28
    åľ¨è¿ĻéĩĮ
    -0.28
    第ä¸Ģ
    -0.27
    åľ¨æѤ
    -0.27
    éķ£
    -0.27
     realmente
    -0.26
    åŁºäºİ
    -0.26
    æŁIJä¸Ģ
    -0.26
    POSITIVE LOGITS
     that
    0.63
    that
    0.54
     That
    0.48
    _that
    0.44
    That
    0.44
    	that
    0.44
     measuring
    0.40
     rằng
    0.38
     THAT
    0.38
     thai
    0.35
    Activations Density 0.004%

    No Known Activations