© 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. 39836
    Prev
    Next
    INDEX
    Explanations

    leader titles followed by possessives or actions

    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
    çĵ¦
    -0.09
    èĦĵ
    -0.09
     ÐijолÑĮ
    -0.09
    ts
    -0.09
    ä¸Ģ个éĩįè¦ģ
    -0.08
    éĴĿ
    -0.08
    èĶº
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    éĽ¹
    -0.08
     Epid
    -0.08
    POSITIVE LOGITS
    åºľ
    0.12
     himself
    0.10
     бил
    0.09
    åıµ
    0.09
    innen
    0.09
    æĸ«
    0.09
    æ´İ
    0.09
    _FUNCTIONS
    0.09
    夫å¦ĩ
    0.09
    åıªä¸º
    0.09
    Activations Density 0.058%

    No Known Activations