© 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. 34141
    Prev
    Next
    INDEX
    Explanations

    positive and negative sentiment 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
    å®īåħ¨æĦŁ
    -0.09
    å®īåħ¨äºĭæķħ
    -0.09
    TEE
    -0.09
    alus
    -0.09
    nis
    -0.09
    è¦ģåĬłå¼º
    -0.09
    è¦ģ好好
    -0.09
    è¦ģ注æĦı
    -0.09
    éľĢè¦ģ注æĦı
    -0.09
    راب
    -0.09
    POSITIVE LOGITS
    æĹłç¼ĺ
    0.10
    æĪIJå°±æĦŁ
    0.09
    èĭ±æīį
    0.09
    IRO
    0.09
    èĬĹ
    0.08
     bul
    0.08
    好äºĭ
    0.08
    åĴĮæĶ¯æĮģ
    0.08
     Fist
    0.08
    ót
    0.08
    Activations Density 0.009%

    No Known Activations