© 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. 52616
    Prev
    Next
    INDEX
    Explanations

    ghost followed by common phrases

    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
    terior
    -0.09
    uki
    -0.09
    oden
    -0.09
    تÙĨ
    -0.09
    nte
    -0.08
    fait
    -0.08
    ction
    -0.08
    ç»ĵæŀľ
    -0.08
    馨
    -0.08
    对ä»ĸ
    -0.08
    POSITIVE LOGITS
    ed
    0.10
     лÑĥÑĩ
    0.10
    ry
    0.09
    åħ¬åı¸ç«łç¨ĭ
    0.09
    ãģıãģªãĤĭ
    0.09
    íĮħ
    0.09
    iet
    0.09
    inks
    0.09
    æ¹ĸåĮº
    0.09
    ory
    0.09
    Activations Density 0.006%

    No Known Activations