© 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. 9669
    Prev
    Next
    INDEX
    Explanations

    conditional statements 'if'

    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
     relax
    -0.08
    è¹²
    -0.08
    cox
    -0.08
    è²Ĥ
    -0.07
    没æľīæĥ³åĪ°
    -0.07
    æĺ¯ä½ł
    -0.07
    NEXT
    -0.07
    ů
    -0.07
    çļĦæĸĩåŃĹ
    -0.07
     forgot
    -0.07
    POSITIVE LOGITS
    è¦ģæĥ³
    0.16
    æīįèĥ½
    0.15
    æīįèĥ½å¤Ł
    0.13
     ÑĩÑĤобÑĭ
    0.12
    为äºĨ让
    0.11
    è¿Ļæł·æīįèĥ½
    0.11
    æĥ³è¦ģ
    0.11
    å¸ĮæľĽèĥ½å¤Ł
    0.10
    为äºĨéģ¿åħį
    0.10
    æĪij们è¦ģ
    0.10
    Activations Density 0.038%

    No Known Activations