© 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. 61806
    Prev
    Next
    INDEX
    Explanations

    borough or canton names

    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
    acen
    -0.10
     liá»ĩu
    -0.10
    åĢ¬
    -0.10
    æĦı大
    -0.09
    .alloc
    -0.09
    ÑĭÑĪ
    -0.09
    tics
    -0.09
    ties
    -0.09
    éĤĥ
    -0.09
    .mo
    -0.09
    POSITIVE LOGITS
    _globals
    0.09
    SEO
    0.08
    çĬģ
    0.08
    INGS
    0.08
    ç¬ij
    0.08
    æIJģ
    0.08
    _px
    0.08
    æĢĿãģĦ
    0.07
    zenie
    0.07
    èĿĹ
    0.07
    Activations Density 0.016%

    No Known Activations