© 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. 27-TRANSCODER-HP
    7. 58380
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¸Ģ度
    -0.29
    度
    -0.28
    éĢIJæ¸IJ
    -0.27
     slowly
    -0.27
    åĵ¥
    -0.26
    inces
    -0.26
    稳å®ļ
    -0.25
    èĢģ大
    -0.25
    ä¹ħ
    -0.25
    avadoc
    -0.25
    POSITIVE LOGITS
     attraction
    0.31
     success
    0.29
     arrangement
    0.29
     change
    0.28
     error
    0.28
     invention
    0.27
    æıĴåħ¥
    0.27
     entr
    0.26
     dropout
    0.26
     unnecessary
    0.26
    Activations Density 0.004%

    No Known Activations