© 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. 55222
    Prev
    Next
    INDEX
    Explanations

    bitter- followed by word

    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
    jure
    -0.10
    åĴĮåıijå±ķ
    -0.10
    çŃīæ´»åĬ¨
    -0.09
    ä¹ĭåĨħ
    -0.09
    èļģ
    -0.09
    çIJĨ
    -0.09
    ç°§
    -0.09
    åĬłå¿«åıijå±ķ
    -0.09
    çļĦè¡£æľį
    -0.09
    åįĵè¶Ĭ
    -0.09
    POSITIVE LOGITS
     heavyweight
    0.09
    lag
    0.09
    ÑĢин
    0.08
    SourceType
    0.08
    ych
    0.08
    ãģĭãĤĬ
    0.08
    ç®Ķ
    0.08
    ight
    0.08
    æĬ¬
    0.08
    stab
    0.08
    Activations Density 0.001%

    No Known Activations