© 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. 57483
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying verbs

    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
    æ³ķå®ļ
    -0.08
    碰åĪ°
    -0.08
    使ä¹ĭ
    -0.08
    åı¯èĥ½
    -0.08
    tty
    -0.08
    IQ
    -0.07
    /Area
    -0.07
    主è¦ģä»İäºĭ
    -0.07
    done
    -0.07
    åıªå¥½
    -0.07
    POSITIVE LOGITS
    ç»
    0.10
    ним
    0.10
    æݢ寻
    0.10
    ify
    0.09
    æĬ¤èĤ¤
    0.09
    éĩįä¸Ń
    0.09
     cứu
    0.09
    åıijå±ķ壮大
    0.09
    åıijå±ķä¸Ń
    0.09
    å°±å¤ŁäºĨ
    0.09
    Activations Density 0.258%

    No Known Activations