© 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. 35514
    Prev
    Next
    INDEX
    Explanations

    own risk

    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®ļäºĨ
    -0.10
    åıĺäºĨ
    -0.09
    寺
    -0.09
     ÐijеÑģ
    -0.09
     водо
    -0.09
     Tes
    -0.08
    xEA
    -0.08
     Preview
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    ró
    -0.08
    POSITIVE LOGITS
    è¿ĻäºĽä¸ľè¥¿
    0.11
    å´¤
    0.11
    è¿ĻäºĽéĹ®é¢ĺ
    0.10
    éŁ³åĵį
    0.10
    åĨľå®¶
    0.09
    楣
    0.09
    åħĭæĸ¯
    0.09
    å·©
    0.09
    èĻļå¼±
    0.09
    inded
    0.09
    Activations Density 0.005%

    No Known Activations