© 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. 51356
    Prev
    Next
    INDEX
    Explanations

    County 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
    æİİ
    -0.10
    é«ĺåİŁ
    -0.10
    æįĭ
    -0.09
     tình
    -0.09
    åĭº
    -0.09
    ابÙĦ
    -0.09
     заÑıв
    -0.08
    éľ²å¤©
    -0.08
    é¤į
    -0.08
    aida
    -0.08
    POSITIVE LOGITS
    åľŁåľ°
    0.08
    sw
    0.08
    unce
    0.08
    oke
    0.08
    keit
    0.08
    wood
    0.08
    achable
    0.08
    onor
    0.08
    ÙĪÙĨØ©
    0.08
    çıŃéķ¿
    0.08
    Activations Density 0.014%

    No Known Activations