© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37786
    Prev
    Next
    INDEX
    Explanations

    relative clauses

    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
    à¹ĥà¸Ī
    -0.09
    ç´¯
    -0.09
    éĤ£æ®µ
    -0.08
    бол
    -0.08
    tin
    -0.08
    å¼Ĥåľ°
    -0.08
    ç®ĹäºĨ
    -0.08
    ders
    -0.08
    ante
    -0.08
    éºĴ
    -0.08
    POSITIVE LOGITS
    unar
    0.09
     PROCUREMENT
    0.09
    è°ĭ
    0.08
    _DT
    0.08
    clus
    0.08
    ely
    0.08
    åħ³ä¹İ
    0.08
    zens
    0.08
    éĩijåŃĹ
    0.08
    å®Ĺ
    0.08
    Activations Density 0.291%

    No Known Activations