© 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. 54506
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    imen
    -0.29
    en
    -0.27
     K
    -0.27
    sse
    -0.26
    sitemap
    -0.26
    æİ¥åľ°
    -0.26
    enes
    -0.26
    argo
    -0.25
    atz
    -0.25
     KV
    -0.25
    POSITIVE LOGITS
     Sellers
    0.25
    åģľäº§
    0.25
    çĶŁæĢģ
    0.25
    ffffffff
    0.25
    iod
    0.25
    è²·ãģĨ
    0.24
    lix
    0.24
    ecedor
    0.24
    çĶŁæĢģçݯå¢ĥ
    0.24
    NOP
    0.23
    Activations Density 0.003%

    No Known Activations