© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    magnitude and role

    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
    ICAST
    -0.10
    å°Ħ
    -0.09
    ÑģÑĤвеннÑĭе
    -0.09
    æľī人
    -0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.09
    archy
    -0.09
     Dod
    -0.08
    亲çĪ±
    -0.08
    èݲ
    -0.08
    æĬij
    -0.08
    POSITIVE LOGITS
    ä¸Ģå°ģ
    0.09
    è¿Ļæł·ä¸Ģ个
    0.09
    åݻ买
    0.09
    æľĢä½İ
    0.09
    ä¸ĢåIJ¬
    0.09
    åĮ¡
    0.09
    ÑĤик
    0.08
    ocard
    0.08
    æ®ĩ
    0.08
    åĪ¶
    0.08
    Activations Density 0.326%

    No Known Activations