© 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. 52626
    Prev
    Next
    INDEX
    Explanations

    Spar

    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
     PackageManager
    -0.30
    oten
    -0.27
    ç¡Ĵ
    -0.26
    quot
    -0.24
    otel
    -0.24
     Salem
    -0.24
    orsi
    -0.24
    irms
    -0.24
    ((&
    -0.23
     attended
    -0.23
    POSITIVE LOGITS
    è¡Į
    0.34
    æ¯į
    0.33
    声
    0.33
    ç£ģ
    0.29
    åĭĥåĭĥ
    0.27
    åIJĦè¡Į
    0.27
     Row
    0.27
    row
    0.27
    ernational
    0.26
    æ´»
    0.26
    Activations Density 0.015%

    No Known Activations