© 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. 22952
    Prev
    Next
    INDEX
    Explanations

    any followed by adjectives

    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
    ä¹ĭ称
    -0.12
    åĪĨä¼ļ
    -0.10
    ä¹ĭåŁİ
    -0.10
     Boeh
    -0.09
    éĢļè¡Įè¯ģ
    -0.09
    çĦ¶åIJİåĨį
    -0.09
    åŃIJéĩĮ
    -0.09
    éľİ
    -0.09
    ä¹ĭæĹħ
    -0.08
    edly
    -0.08
    POSITIVE LOGITS
    åħ¨æ°ij
    0.09
    OfClass
    0.09
    éĥ¨åĪĨåĨħ容
    0.09
    /all
    0.09
    ä¸Ģéĥ¨åĪĨ
    0.08
     Rew
    0.08
    çĽħ
    0.08
    ATAB
    0.08
    istar
    0.08
     Eleanor
    0.08
    Activations Density 0.099%

    No Known Activations