© 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. 43896
    Prev
    Next
    INDEX
    Explanations

    research articles

    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
    houses
    -0.27
    åIJĪæ³ķ
    -0.25
     Undert
    -0.25
    æijĺç¼ĸ
    -0.24
    ä¸Ģ群
    -0.24
    aurants
    -0.24
    åįıåķĨ
    -0.24
    sampling
    -0.23
     PageInfo
    -0.23
     molecules
    -0.23
    POSITIVE LOGITS
     target
    0.38
    ress
    0.30
    target
    0.29
    erver
    0.29
    alt
    0.28
    оз
    0.28
    éħį
    0.28
    _TARGET
    0.28
    Target
    0.27
    _target
    0.27
    Activations Density 0.001%

    No Known Activations