© 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. 52736
    Prev
    Next
    INDEX
    Explanations

    code and web development

    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
    #echo
    -0.26
    åıijéŁ³
    -0.25
    åıij
    -0.24
    ä¿ĿåĪ©
    -0.24
    oping
    -0.24
    æĪijä¸įæĥ³
    -0.23
    å®Ŀå®ī
    -0.23
    prog
    -0.23
    kov
    -0.23
    APO
    -0.23
    POSITIVE LOGITS
    ada
    0.29
    hr
    0.27
    åħ°èĬ±
    0.27
    éĥ¯
    0.25
    hu
    0.24
    etrain
    0.24
    eneric
    0.24
     strategically
    0.24
    é«ĺå³°
    0.24
     KE
    0.23
    Activations Density 0.016%

    No Known Activations