© 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. 31094
    Prev
    Next
    INDEX
    Explanations

    media types followed by status

    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
    å°±è§īå¾Ĺ
    -0.10
    ä¼ļè§īå¾Ĺ
    -0.09
    å°±çŁ¥éģĵ
    -0.09
    åīľ
    -0.09
    äºĨåIJĹ
    -0.09
    æ¯ı次éĥ½
    -0.09
    å°±å¤ŁäºĨ
    -0.08
    ç¼ķ
    -0.08
    illy
    -0.08
    å§Ĭ妹
    -0.07
    POSITIVE LOGITS
    çĶ±ä¸ŃåĽ½
    0.10
    åİŁæľ¬
    0.10
    ä¹ŁåĽłæѤ
    0.09
    çĶ±
    0.09
    çļĦåħ·ä½ĵ
    0.09
    _AST
    0.09
     поÑģколÑĮ
    0.09
    ä¸ºæľŁ
    0.08
    主è¦ģåĮħæĭ¬
    0.08
     includes
    0.08
    Activations Density 0.284%

    No Known Activations