© 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. 50625
    Prev
    Next
    INDEX
    Explanations

    tort, tortoise, tortilla, tortious

    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
    åĨ¢
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    ARP
    -0.09
    æºĺ
    -0.09
    èĹģ
    -0.09
    åı£ä¸Ń
    -0.09
    éĹ»
    -0.09
    odule
    -0.09
    ivers
    -0.08
    atures
    -0.08
    POSITIVE LOGITS
    feas
    0.10
    WithOptions
    0.10
    unately
    0.09
    åĬŀåħ¬åİħ
    0.09
    unate
    0.09
     Stanley
    0.09
    folio
    0.09
    делÑĮ
    0.09
    _WORDS
    0.09
    anker
    0.09
    Activations Density 0.008%

    No Known Activations