© 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. 35340
    Prev
    Next
    INDEX
    Explanations

    months and seasons

    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
    night
    -0.11
    å¤ľ
    -0.10
    ERE
    -0.10
    ä¹ĭå¤ľ
    -0.09
    nable
    -0.09
    ç´¯äºĨ
    -0.09
    çĥĽ
    -0.09
    å¹´ç»Ī
    -0.08
    åĽĽæĸ¹
    -0.08
    绿è±Ĩ
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹ĪæŶåĢĻ
    0.09
    svc
    0.09
    ()(
    0.08
    ä¸Ģçľ¼
    0.08
    æ®·
    0.08
    rama
    0.08
    lda
    0.08
    éĥİ
    0.08
    丰
    0.08
    ä½ķæŶ
    0.08
    Activations Density 0.050%

    No Known Activations