© 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. 56139
    Prev
    Next
    INDEX
    Explanations

    sports actions

    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
    éĶ¤
    -0.09
    çĺ¦
    -0.09
    æį¶
    -0.09
    ç»ĵæŀľæĺ¾ç¤º
    -0.08
    å¸ħ
    -0.08
    å¥ĩ
    -0.08
     remot
    -0.08
    sis
    -0.08
     Bed
    -0.08
     Riley
    -0.08
    POSITIVE LOGITS
    æī¯
    0.10
    inspace
    0.09
    yte
    0.09
    çĽijå¯Ł
    0.09
    NBC
    0.09
    altitude
    0.09
    彩
    0.09
    çķĮ第ä¸Ģ
    0.08
    说åĩºæĿ¥
    0.08
    é¢ģ
    0.08
    Activations Density 0.010%

    No Known Activations