© 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. 10657
    Prev
    Next
    INDEX
    Explanations

    et al. [@CR]

    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
    åĩºåĬ¨
    -0.09
    çĶ±ä¸ŃåĽ½
    -0.09
    éļĪ
    -0.09
    éĿ¢åŃĶ
    -0.08
    tle
    -0.08
    anon
    -0.08
    _regularizer
    -0.08
    以便
    -0.08
    åĬª
    -0.08
    pond
    -0.08
    POSITIVE LOGITS
     spills
    0.10
    æľīçĶ¨
    0.09
    注è§Ĩ
    0.08
    èĬŃ
    0.08
    æĮĩ导ä¸ĭ
    0.08
    äºĶæĺŁ
    0.08
    åĸľæĤ¦
    0.08
    fsp
    0.08
    âĩĭ
    0.08
    综åIJĪæ²»çIJĨ
    0.08
    Activations Density 0.293%

    No Known Activations