© 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. 10528
    Prev
    Next
    INDEX
    Explanations

    javascript browser console hooks

    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
    éĩİå¿ĥ
    -0.10
     mù
    -0.09
     Rug
    -0.09
    è¯Ħ级
    -0.09
    æݥ纳
    -0.09
    æį§
    -0.08
    ä»ĭ
    -0.08
    andin
    -0.08
    æĢĢæĬ±
    -0.08
    åĪĿåĪĽ
    -0.08
    POSITIVE LOGITS
    ilent
    0.10
    ä½ĵåĬĽ
    0.09
    Ñģад
    0.09
    寻
    0.09
    pekt
    0.08
    麻çĹ¹
    0.08
    æĬ¤èº«ç¬¦
    0.08
    梯
    0.08
    adow
    0.08
    æĶ»åħ³
    0.08
    Activations Density 0.280%

    No Known Activations