© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40040
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    家
    -0.28
    ieux
    -0.26
    Numer
    -0.25
    åŀĴ
    -0.23
    èĬĤå¥ı
    -0.23
     Glam
    -0.23
    æľ¬æľĪ
    -0.23
    èĩªèIJ¥
    -0.23
    é¢ĦåĶ®
    -0.23
     Aura
    -0.22
    POSITIVE LOGITS
    è´£ç¼ĸ
    0.27
    çĺ¦
    0.24
    æĦıè§ģåıįé¦Ī
    0.24
     apprec
    0.24
    _eg
    0.24
    á»Ĺ
    0.24
    çĴł
    0.23
     dissert
    0.23
     CONTRACT
    0.23
    zug
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.