© 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. 11313
    Prev
    Next
    INDEX
    Explanations

    proper nouns or abbreviations like COMPANY, Castle, Poland

    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
    itech
    -0.09
    æ¦Ħ
    -0.09
    å¼Ĥ
    -0.08
    çķ°
    -0.08
    _spot
    -0.08
    åıĻ
    -0.08
    лав
    -0.08
    'Brien
    -0.08
    æµ·åĨĽ
    -0.07
    _iff
    -0.07
    POSITIVE LOGITS
    _c
    0.21
    _C
    0.19
    ï½ĥ
    0.18
     c
    0.17
    æľīéĻIJ责任
    0.16
    C
    0.16
    ï¼£
    0.16
    	C
    0.15
     C
    0.15
    ðĿIJ¶
    0.15
    Activations Density 0.543%

    No Known Activations