© 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. 32211
    Prev
    Next
    INDEX
    Explanations

    no refund or credit

    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
    IES
    -0.10
    åĥ»
    -0.09
    ä¸Ģ件äºĭæĥħ
    -0.09
    itzer
    -0.09
    åłª
    -0.09
     Barcl
    -0.08
    åħ¼é¡¾
    -0.08
    åĿļå®Ī
    -0.08
     ged
    -0.08
    _MA
    -0.08
    POSITIVE LOGITS
    phans
    0.09
    èĭ¹
    0.09
    æĵį
    0.09
    دÙĦ
    0.09
    çľ©
    0.09
    çĹ¹
    0.09
    ibles
    0.09
    çĹĽèĭ¦
    0.09
    ç¿ĺ
    0.09
    ä¸ĥæĺŁ
    0.08
    Activations Density 0.069%

    No Known Activations