© 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. 40877
    Prev
    Next
    INDEX
    Explanations

    say "going" or "gonna"

    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
    Negative Logits
    åį³å°Ĩ
    -0.27
    cial
    -0.27
    aleigh
    -0.27
     Being
    -0.26
    Being
    -0.26
     Charge
    -0.26
    charge
    -0.25
     charge
    -0.25
     Büyük
    -0.24
    pragma
    -0.24
    POSITIVE LOGITS
     go
    0.41
    g
    0.37
     g
    0.36
    G
    0.36
    GO
    0.33
    Go
    0.32
    GG
    0.32
    _g
    0.31
    	go
    0.31
    æĪĪ
    0.31
    Activations Density 0.009%

    No Known Activations