© 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. 17904
    Prev
    Next
    INDEX
    Explanations

    place names ending in ton or ham

    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
    ings
    -0.11
    åħ¶ä¸Ńæľī
    -0.10
    -0.10
    ochen
    -0.09
    éħ
    -0.09
    lessly
    -0.09
    usch
    -0.09
    INGS
    -0.09
    èĵŁ
    -0.09
    cape
    -0.09
    POSITIVE LOGITS
    enuity
    0.10
    eous
    0.10
     лиÑĪÑĮ
    0.10
    ieur
    0.10
    ãģĹãģ¾ãģĨ
    0.09
    red
    0.09
    ripp
    0.09
    IME
    0.09
    ue
    0.09
    ories
    0.09
    Activations Density 0.009%

    No Known Activations