© 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. 34368
    Prev
    Next
    INDEX
    Explanations

    miss any, miss a, miss some

    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
    åĥ§
    -0.10
    èijŃ
    -0.08
    åĽ½æľī
    -0.08
    èĢ½è¯¯
    -0.08
     Mer
    -0.08
     inc
    -0.08
    èĩªçĦ¶çķĮ
    -0.08
    æıIJéĢŁ
    -0.08
    sing
    -0.08
    åĨįåİ»
    -0.08
    POSITIVE LOGITS
     دÙĬ
    0.10
    çĦĺ
    0.10
    讫
    0.09
    eni
    0.08
    éĥ½ä¸įèĥ½
    0.08
    uhan
    0.08
    æĢģ
    0.08
     bif
    0.08
    è¹Ħ
    0.08
    æīĵæī«
    0.08
    Activations Density 0.012%

    No Known Activations