© 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. 27548
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation or evidence

    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
    骸
    -0.10
    kok
    -0.10
    onen
    -0.10
    éĵ¶è¡Įä¸ļ
    -0.09
    èįļ
    -0.09
    çĵ·çłĸ
    -0.09
    åIJİåĨį
    -0.08
    ä¹ĭå¿ĥ
    -0.08
    aira
    -0.08
    ripe
    -0.08
    POSITIVE LOGITS
    è¿ĩæĪ·
    0.08
    inet
    0.08
    çļĭ
    0.08
    عÙĦاÙħ
    0.08
     подÑħод
    0.08
    rı
    0.08
     Prest
    0.08
    عبر
    0.07
    gó
    0.07
     ÑįÑĤ
    0.07
    Activations Density 0.071%

    No Known Activations