© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37897
    Prev
    Next
    INDEX
    Explanations

    database schemas

    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
    aggi
    -0.10
    ä¹ĭ家
    -0.09
    atives
    -0.09
    alse
    -0.09
    åĬ¼
    -0.09
    ovi
    -0.09
    æłī
    -0.09
    alytics
    -0.09
    andard
    -0.09
    ibs
    -0.09
    POSITIVE LOGITS
    ase
    0.12
    ruptcy
    0.11
    elling
    0.10
    rupt
    0.09
    pedia
    0.09
    eros
    0.09
     Milo
    0.09
    袱
    0.08
    è¾
    0.08
    Ñģ
    0.08
    Activations Density 0.128%

    No Known Activations