© 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. 3783
    Prev
    Next
    INDEX
    Explanations

    -able adjectives followed by prepositions

    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
    便äºİ
    -0.09
    åij¸
    -0.08
    æĤĦæĤĦ
    -0.08
    SY
    -0.08
    æĪ¿åŃIJ
    -0.08
    SYS
    -0.08
    /general
    -0.07
    NEWS
    -0.07
    mans
    -0.07
    ä¸įæķ¢
    -0.07
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.11
    åIJĦ个æĸ¹éĿ¢
    0.09
    ä¸Ģå®ļç¨ĭ度
    0.09
    缸åħ³éĥ¨éŨ
    0.09
    ä¸Ģå®ļ
    0.09
    鲨
    0.09
    çĶ¬
    0.09
    adian
    0.09
    踹
    0.08
    å½ĵä½ľ
    0.08
    Activations Density 0.094%

    No Known Activations