© 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. 19896
    Prev
    Next
    INDEX
    Explanations

    as if or as though

    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
    thro
    -0.09
    ãģ¨ãĤĬ
    -0.08
    ä¸İæŶ
    -0.08
    èĻ±
    -0.08
    ace
    -0.08
    没人
    -0.08
    æīĵæŃ»
    -0.08
    缸éĢļ
    -0.07
    adm
    -0.07
    è¶Ĭ
    -0.07
    POSITIVE LOGITS
    就好åĥı
    0.18
    好åĥıæĺ¯
    0.17
    ä»¿ä½Ľ
    0.17
    好åĥı
    0.16
    好象
    0.16
    好似
    0.15
    åĥıæĺ¯
    0.14
    å°±åĥıæĺ¯
    0.13
    ä¼¼ä¹İæĺ¯
    0.10
    éħļ
    0.10
    Activations Density 0.054%

    No Known Activations