© 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. 52651
    Prev
    Next
    INDEX
    Explanations

    code/computer text

    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
    igt
    -0.28
    avour
    -0.27
     apl
    -0.26
    红èĮ¶
    -0.25
     Stanton
    -0.25
    ÑĥÑīе
    -0.25
    uba
    -0.24
    ÑģÑĤÑĢа
    -0.24
    Cons
    -0.24
    aval
    -0.24
    POSITIVE LOGITS
    ci
    0.26
    -ci
    0.26
     ci
    0.26
    골
    0.26
    åī¯ä¸»å¸Ń
    0.25
    æĿ¡
    0.25
    hart
    0.24
    callbacks
    0.24
    omat
    0.24
    omid
    0.24
    Activations Density 0.003%

    No Known Activations