© 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. 56936
    Prev
    Next
    INDEX
    Explanations

    program or intervention

    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
    è¿Ļåĩłä¸ª
    -0.10
    åį±
    -0.09
    ä¸įåħ¬å¹³
    -0.09
    èĢĥ試
    -0.09
    èĪ·
    -0.09
    liqu
    -0.08
    椿
    -0.08
    èĢ¶
    -0.08
    çĬ¶æĢģä¸ĭ
    -0.08
    ç»Į
    -0.08
    POSITIVE LOGITS
    å¹²é¢Ħ
    0.13
     intervention
    0.10
    ÐļÑĥÑĢÑģ
    0.10
    /boot
    0.10
    çĸĹ
    0.10
    æĪIJåĬŁ
    0.10
     interventions
    0.10
    essions
    0.10
    çŃĭ
    0.09
     programs
    0.09
    Activations Density 0.215%

    No Known Activations