© 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. 31369
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or state

    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
    康
    -0.10
    让
    -0.10
    æıŃ
    -0.09
    bia
    -0.09
     Inspir
    -0.09
    å¼ķåıijäºĨ
    -0.08
    .isOn
    -0.08
     COPYRIGHT
    -0.08
    å±ķçİ°äºĨ
    -0.08
    ató
    -0.08
    POSITIVE LOGITS
    åīįæīĢæľªæľī
    0.12
    çĮľ
    0.10
    çĪ¬ä¸Ĭ
    0.09
    éĵ¤
    0.08
    æĸ°åŁºå»º
    0.08
    以æĿ¥
    0.08
    çĹ¹
    0.08
    ingo
    0.08
    io
    0.08
    以ä¾Ĩ
    0.08
    Activations Density 0.104%

    No Known Activations