© 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. 5509
    Prev
    Next
    INDEX
    Explanations

    comic book characters and events

    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
    æ±Łå±±
    -0.11
    åıŁ
    -0.10
    æ¢ĵ
    -0.10
    rate
    -0.09
    表çĻ½
    -0.08
    åı¸
    -0.08
    çĦķ
    -0.08
    åĪ¶åº¦æĶ¹éĿ©
    -0.08
    ä¸Ģæīĭ
    -0.08
    å¼ĢèĬ±
    -0.08
    POSITIVE LOGITS
    æ±ĩ
    0.10
    roma
    0.10
    åĿIJ
    0.09
    çı¾
    0.09
    ings
    0.09
     СмоÑĤÑĢ
    0.09
    ç»Ħè£ħ
    0.09
    eps
    0.08
    hiro
    0.08
    INGS
    0.08
    Activations Density 0.005%

    No Known Activations