© 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. 20042
    Prev
    Next
    INDEX
    Explanations

    so/very/really + adverb/much

    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
     TNT
    -0.09
     полÑĥÑĩи
    -0.09
    verse
    -0.09
     Lamp
    -0.08
    sect
    -0.08
    解åĨ³éĹ®é¢ĺ
    -0.08
    æ²»å®ī
    -0.08
    äºĨä¸Ģæī¹
    -0.08
    äºĨä¸Ģç³»åĪĹ
    -0.08
    еÑģÑĤв
    -0.08
    POSITIVE LOGITS
    ä¹ħäºĨ
    0.11
    ç¿ķ
    0.10
    çģı
    0.09
    ÑĩÑĥв
    0.09
    ä¹ħ
    0.09
    orges
    0.09
    æĹłéļľç¢į
    0.09
    éĢļè¿ĩ对
    0.09
    ä¸įéĢļ
    0.09
    æİ·
    0.08
    Activations Density 0.052%

    No Known Activations