© 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. 39685
    Prev
    Next
    INDEX
    Explanations

    packed for an event, line for tickets, bid on an item

    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
    çŁ¾
    -0.09
    港澳
    -0.09
    ajar
    -0.09
    åĨ¬å¥¥
    -0.09
    guarded
    -0.08
    åŁĻ
    -0.08
    éĩįçĤ¹
    -0.08
    åĬ¡å·¥
    -0.08
    abad
    -0.08
    "https
    -0.08
    POSITIVE LOGITS
    å°±æĺ¯ä¸ºäºĨ
    0.10
    缮çĿ¹
    0.09
    äºī缸
    0.09
    åĽ´
    0.09
    inton
    0.08
    åīįæīĢæľªæľī
    0.08
    ì¢ħ
    0.08
    纷纷
    0.08
    è§ģè¯ģäºĨ
    0.08
    纷纷表示
    0.08
    Activations Density 0.206%

    No Known Activations