© 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. 23534
    Prev
    Next
    INDEX
    Explanations

    plant extracts and products

    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
    fly
    -0.09
    èĿĺ
    -0.09
    å¥Ķé©°
    -0.09
    è£Ĥ
    -0.09
     Flake
    -0.09
     Dew
    -0.08
    hetto
    -0.08
    åŃĺ
    -0.08
    edom
    -0.08
    å°ģ
    -0.08
    POSITIVE LOGITS
    æŀľ
    0.10
    æ¾Ħæ¸ħ
    0.10
    åı¯çĶ¨äºİ
    0.10
    æĺİæĻº
    0.09
    æµĨ
    0.09
    å¾Ĺ天
    0.09
    天çĶŁ
    0.09
    èĬ±èįī
    0.09
    AIL
    0.09
    åºŁæ°´
    0.09
    Activations Density 0.064%

    No Known Activations