© 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. 43887
    Prev
    Next
    INDEX
    Explanations

    say "the ending -brate"

    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
    ate
    -0.30
    ages
    -0.30
    #line
    -0.29
     organ
    -0.28
    ány
    -0.28
    otype
    -0.28
    apsed
    -0.27
    aze
    -0.27
    icing
    -0.27
     wireType
    -0.26
    POSITIVE LOGITS
    åį´è¢«
    0.33
    çĿ¡
    0.27
    æĸ¯çī¹
    0.27
    ERAL
    0.27
    éĹľ
    0.26
    .Pos
    0.25
    æĦ¿
    0.25
    ê´Ģê³Ħ
    0.25
    Sleep
    0.25
    å¤ķ
    0.24
    Activations Density 0.002%

    No Known Activations