© 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. 33-TRANSCODER-HP
    7. 52529
    Prev
    Next
    INDEX
    Explanations

    trying/try

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    TO
    -0.33
    -č↵
    -0.27
     difÃŃc
    -0.26
     TO
    -0.25
    el
    -0.25
    è¦ģ
    -0.25
     :-↵
    -0.25
    âĢ¦↵
    -0.24
    à¸Ĺ
    -0.24
    ’s
    -0.24
    POSITIVE LOGITS
     figure
    0.38
    figure
    0.32
     count
    0.31
    å¸Ĥåľºä¸»ä½ĵ
    0.30
    figures
    0.29
     keep
    0.28
     ingest
    0.28
    efully
    0.28
     measure
    0.27
     scroll
    0.27
    Activations Density 0.069%

    No Known Activations