© 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. 63165
    Prev
    Next
    INDEX
    Explanations

    intensifiers preceding 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
    hal
    -0.10
    åĻ©
    -0.09
     hal
    -0.09
    羣缸
    -0.09
    msp
    -0.08
     اÙĦÙħزÙĬد
    -0.08
    .raise
    -0.08
    æĥŃ
    -0.08
    ç¿»è¯ij
    -0.08
    ç§ĺ
    -0.08
    POSITIVE LOGITS
    çĪ±åĽ½ä¸»ä¹ī
    0.09
    æķ°çĽ®
    0.09
    æīĭä¸ŃçļĦ
    0.09
    åıĤä¸İåĪ°
    0.09
     diy
    0.09
    ç¹ģå¿Ļ
    0.09
    å¿Ļç¢Į
    0.09
    ä¾Ŀ
    0.09
    売ãĤĮ
    0.09
     Ñĥзн
    0.09
    Activations Density 0.060%

    No Known Activations