© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8234
    Prev
    Next
    INDEX
    Explanations

    wheel, rim, tire, alloy

    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
    ä¸įåıĹ
    -0.10
     Pend
    -0.09
    èĩŃ
    -0.09
    lemn
    -0.09
    SCAN
    -0.09
    yat
    -0.09
    æ°ijå±ħ
    -0.09
    è´½
    -0.08
     Filed
    -0.08
    éģij
    -0.08
    POSITIVE LOGITS
    æ¯Ĥ
    0.13
    åĪ·
    0.11
    éķ«
    0.09
    åĩ¹
    0.09
    Interpolator
    0.08
    åĨĹ
    0.08
    åħ¨æĹ¥åĪ¶
    0.08
     Sud
    0.08
    sert
    0.08
    éĶ£
    0.08
    Activations Density 0.070%

    No Known Activations