© 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. 27386
    Prev
    Next
    INDEX
    Explanations

    places ending in lands or towns

    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
    éĴ§
    -0.11
    SION
    -0.09
    Convertible
    -0.08
    èĪľ
    -0.08
     Gabri
    -0.08
    纣
    -0.08
     Kirst
    -0.07
    éĥ¨éķ¿
    -0.07
    idal
    -0.07
    ruz
    -0.07
    POSITIVE LOGITS
    é£İè²Į
    0.09
    èįŁ
    0.08
    ophile
    0.08
    IRC
    0.08
     trÃł
    0.08
    ë§ģ
    0.08
    ово
    0.08
     vụ
    0.08
    èľĵ
    0.08
    ipy
    0.08
    Activations Density 0.006%

    No Known Activations