© 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. 56223
    Prev
    Next
    INDEX
    Explanations

    sign up / register

    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
    ä¸Ģ家
    -0.09
     liv
    -0.09
    ey
    -0.09
    roud
    -0.09
    HDR
    -0.09
    eful
    -0.08
    çĭŃ
    -0.08
    Guest
    -0.08
    liv
    -0.08
    è¿ĽéŨ
    -0.08
    POSITIVE LOGITS
    çī
    0.09
    è¾ĵ
    0.09
    æĿ¥çľĭçľĭåIJ§
    0.08
    æģ°æģ°
    0.08
    agic
    0.08
     è¾ĵ
    0.08
    _WORDS
    0.08
    /tutorial
    0.08
    çĢı
    0.08
    åĩ¡æľ¬ç½ij
    0.08
    Activations Density 0.153%

    No Known Activations