© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    bacon dishes and strips

    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
    åIJIJ
    -0.11
    lexport
    -0.10
    饮åĵģ
    -0.10
    饮çĶ¨
    -0.10
     Drinks
    -0.10
    _MISS
    -0.09
    _PHP
    -0.09
    èĮķ
    -0.09
    iage
    -0.09
    伤
    -0.09
    POSITIVE LOGITS
    æ·Ħ
    0.11
    åį·
    0.10
    æĭ±
    0.10
    ç¼ī
    0.08
    .enum
    0.08
    æ¼³
    0.08
    éªij
    0.08
    Roll
    0.08
    çĮª
    0.08
    çĥŁ
    0.08
    Activations Density 0.010%

    No Known Activations