© 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. 54729
    Prev
    Next
    INDEX
    Explanations

    to

    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
     complete
    -0.32
    anners
    -0.29
     Complete
    -0.28
    å®Įæķ´
    -0.28
    reme
    -0.28
    Complete
    -0.27
    é¡¹çĽ®çļĦ
    -0.27
     pocket
    -0.27
    çĽİ
    -0.27
     tens
    -0.26
    POSITIVE LOGITS
    åįıåIJĮåıijå±ķ
    0.26
    åįıè°ĥåıijå±ķ
    0.25
     Blaze
    0.25
     Zus
    0.25
    roman
    0.24
    cod
    0.24
     roman
    0.24
     Barcl
    0.24
    rô
    0.24
     ============================================================================↵
    0.24
    Activations Density 0.043%

    No Known Activations