© 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. 41141
    Prev
    Next
    INDEX
    Explanations

    it

    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
    ophys
    -0.29
    orphic
    -0.28
     Mean
    -0.28
    obox
    -0.27
     mean
    -0.26
    -mean
    -0.25
    ottie
    -0.25
     meant
    -0.25
    mean
    -0.24
    è¿Ļ个è¯į
    -0.24
    POSITIVE LOGITS
     sure
    0.41
     rather
    0.39
    rather
    0.35
    èĢĮéĿŀ
    0.32
     Sure
    0.31
     Rather
    0.30
     am
    0.30
     strikes
    0.29
    Am
    0.29
    sure
    0.28
    Activations Density 0.013%

    No Known Activations