© 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. 52606
    Prev
    Next
    INDEX
    Explanations

    non-English 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
    boa
    -0.27
    ken
    -0.26
    åĽ½æľī
    -0.25
    pets
    -0.25
    frm
    -0.24
    åīįåIJİ
    -0.24
    ucken
    -0.24
     Cler
    -0.24
     ushort
    -0.24
    追踪
    -0.24
    POSITIVE LOGITS
    åį·
    0.29
    æ³°
    0.28
    Tube
    0.26
    éĿ
    0.26
    endance
    0.25
    Renderer
    0.25
    ipur
    0.25
    æŁ¬
    0.25
     Aim
    0.25
    enstein
    0.25
    Activations Density 0.008%

    No Known Activations