© 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. 31855
    Prev
    Next
    INDEX
    Explanations

    establish, consolidate, cement

    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
    åı¬åĶ¤
    -0.09
    é¢Ħè§ģ
    -0.09
    à¸ļรร
    -0.09
    attering
    -0.09
    angu
    -0.09
    ittings
    -0.09
    lena
    -0.08
    ìĹĺ
    -0.08
    IGH
    -0.08
    æĹłåģ¿
    -0.08
    POSITIVE LOGITS
    å·©åĽº
    0.20
    çī¢åĽº
    0.20
    ç¨³åĽº
    0.19
    çī¢
    0.15
    æīİå®ŀ
    0.15
    åĬłæ·±
    0.14
     firmly
    0.14
    åĽºåĮĸ
    0.13
    åĿļå®ŀ
    0.13
     vững
    0.13
    Activations Density 0.205%

    No Known Activations