© 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. 54784
    Prev
    Next
    INDEX
    Explanations

    rain

    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
    è´¼
    -0.27
    Tit
    -0.27
    je
    -0.26
    å±Ī
    -0.26
    ABS
    -0.26
    åĩ¿
    -0.25
    aby
    -0.25
    shots
    -0.25
    çªľ
    -0.25
     clim
    -0.25
    POSITIVE LOGITS
     Gone
    0.31
     donors
    0.27
    endum
    0.25
    iosk
    0.25
     donor
    0.25
    iola
    0.25
     Paolo
    0.25
    ãĥľãĥ¼
    0.24
    overn
    0.24
     Park
    0.24
    Activations Density 0.015%

    No Known Activations