© 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. 22568
    Prev
    Next
    INDEX
    Explanations

    been followed by time or duration

    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
    å½»
    -0.12
    èĥŀ
    -0.10
    åħĪè¡Į
    -0.10
    浪费
    -0.09
    onde
    -0.09
    çľģæķĻèĤ²
    -0.09
    	TokenName
    -0.09
    çľģéĴ±
    -0.09
    æī¯
    -0.09
    usercontent
    -0.09
    POSITIVE LOGITS
    å¤ļä¹ħ
    0.10
    å¾Īä¹ħ
    0.10
    ä¸Ģ段æŶéĹ´
    0.09
    太ä¹ħ
    0.09
    ied
    0.09
     awhile
    0.09
    ned
    0.09
    eft
    0.09
     Reflex
    0.09
    ines
    0.08
    Activations Density 0.173%

    No Known Activations