© 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. 35248
    Prev
    Next
    INDEX
    Explanations

    return or terms

    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
    iveness
    -0.11
    \/\/
    -0.10
    /Area
    -0.09
     поÑĩ
    -0.09
    åħļæĶ¿
    -0.09
    çİŁ
    -0.09
    åĽ¹
    -0.09
    ivals
    -0.09
    æĸĹäºī
    -0.09
    ä¸įç¡®å®ļ
    -0.09
    POSITIVE LOGITS
    èµı
    0.10
     ble
    0.10
    æŃ£å½ĵ
    0.09
    bek
    0.09
    ä¾Ľåħ»
    0.08
    dsp
    0.08
     иÑģкÑĥÑģÑģÑĤв
    0.08
    è³ŀ
    0.08
    abis
    0.08
    bles
    0.08
    Activations Density 0.001%

    No Known Activations