© 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. 54832
    Prev
    Next
    INDEX
    Explanations

    He or Be

    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
    inic
    -0.26
    ÙĪص
    -0.26
     radi
    -0.26
    æį¢
    -0.26
    å§Ķå®£ä¼ł
    -0.25
    -hidden
    -0.24
    éļĺ
    -0.24
    porate
    -0.24
    å¤ĸåĽ´
    -0.24
    ç®Ģåįķ
    -0.23
    POSITIVE LOGITS
    åĴ¯
    0.32
    imei
    0.28
     suprem
    0.27
     pl
    0.27
    hil
    0.26
    .pl
    0.25
    æ¶Ĥ
    0.25
    inceton
    0.25
    Pl
    0.25
    ging
    0.25
    Activations Density 0.099%

    No Known Activations