© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1554
    Prev
    Next
    INDEX
    Explanations

    another followed by a number or group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mere
    -0.08
    SESSION
    -0.08
    飨
    -0.08
    ä¿¡ç®±
    -0.08
    enment
    -0.08
    developers
    -0.08
    俨
    -0.08
    ียม
    -0.08
    athed
    -0.07
     Rescue
    -0.07
    POSITIVE LOGITS
    another
    0.12
    åı¦ä¸Ģä½į
    0.12
    åı¦ä¸Ģ个
    0.12
     another
    0.11
    åľ¨ä¸ĢæĹģ
    0.11
    åı¦ä¸Ģ
    0.11
     дÑĢÑĥг
    0.10
    妪
    0.10
    åı¦è¡Į
    0.10
    åı¦å¤ĸä¸Ģ个
    0.10
    Activations Density 0.085%

    No Known Activations