© 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. 58342
    Prev
    Next
    INDEX
    Explanations

    lists of items or goods

    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
    忧
    -0.12
    èħ¹
    -0.11
    ä¼ģä¸ļåıijå±ķ
    -0.09
    å½°
    -0.09
    缫
    -0.09
     bookstore
    -0.09
    çĹ´
    -0.09
    éĶī
    -0.09
     Exhaust
    -0.09
    温æ³ī
    -0.09
    POSITIVE LOGITS
    çī©åĵģ
    0.19
    ä»Ģä¹Īä¸ľè¥¿
    0.15
     items
    0.13
    çī©ä»¶
    0.12
    å®ŀçī©
    0.12
    éģĵåħ·
    0.12
     objects
    0.11
    items
    0.11
    çī©ä½ĵ
    0.11
    诸å¦Ĥ
    0.11
    Activations Density 0.275%

    No Known Activations