© 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. 23522
    Prev
    Next
    INDEX
    Explanations

    expressing exhaustion

    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
     ObjectType
    -0.09
    æݺ
    -0.09
    èĪ¬
    -0.09
    cker
    -0.09
    TargetException
    -0.08
    éģĩ
    -0.08
    ä»ĭ
    -0.08
    èĦIJ
    -0.08
    (CL
    -0.08
     Wrapped
    -0.08
    POSITIVE LOGITS
    èĥ³èĨĬ
    0.10
    æĻĹ
    0.09
    ç¨Ĺ
    0.09
    è°¤
    0.09
    è¶ħè¿ĩäºĨ
    0.09
    åħħ
    0.09
    èĥ½èĢĹ
    0.09
    å¼ĢéŨ
    0.08
    è¦ģä¹Ī
    0.08
    çľī
    0.08
    Activations Density 0.036%

    No Known Activations