© 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. 1725
    Prev
    Next
    INDEX
    Explanations

    town names and locations

    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
    åijĺ
    -0.10
    itating
    -0.09
    é«ĺãģĦ
    -0.09
    aden
    -0.09
    声åĵį
    -0.09
    ayers
    -0.08
    楯
    -0.08
    åŁĻ
    -0.08
    pery
    -0.08
    å¤ĦåĪĨ
    -0.08
    POSITIVE LOGITS
    liness
    0.13
    aise
    0.10
    ãģ¹ãģį
    0.10
    icz
    0.10
    ราว
    0.09
    iet
    0.09
    åĩ¡æľ¬ç½ij
    0.09
    eh
    0.09
    pis
    0.09
     lá»ĩ
    0.09
    Activations Density 0.014%

    No Known Activations