© 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. 20348
    Prev
    Next
    INDEX
    Explanations

    in + prepositional phrase

    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
    æĺ¨æĹ¥
    -0.10
    èī®
    -0.10
    regs
    -0.09
    ENCH
    -0.09
    .export
    -0.09
    <Address
    -0.09
    irable
    -0.09
    Ñģкоп
    -0.09
    天ä¸ĭ
    -0.09
    笨
    -0.09
    POSITIVE LOGITS
     Tier
    0.09
    Tier
    0.09
    ä¸ĭåįĬå¹´
    0.09
    éĻ·
    0.09
    Ñıд
    0.08
    æ·
    0.08
    oy
    0.08
    å¾ľ
    0.08
    odie
    0.08
    åľ¨ç½ijä¸Ĭ
    0.08
    Activations Density 0.176%

    No Known Activations