© 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. 54669
    Prev
    Next
    INDEX
    Explanations

    camera and image processing

    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
    shot
    -0.36
    å°Ħ
    -0.33
     shot
    -0.33
     Shot
    -0.30
    shots
    -0.29
     shoots
    -0.29
    _shot
    -0.28
     shots
    -0.27
     Shots
    -0.27
     Mur
    -0.26
    POSITIVE LOGITS
    ↵                    ↵
    0.28
     programmed
    0.25
    makt
    0.25
    ,copy
    0.25
    ertino
    0.24
    /frontend
    0.24
    ↵            ↵
    0.24
    angelog
    0.24
    è¿ĺæĺ¯è¦ģ
    0.23
    lish
    0.23
    Activations Density 0.066%

    No Known Activations