© 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. 10647
    Prev
    Next
    INDEX
    Explanations

    grandparents and grandchildren

    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
    ç¿©
    -0.12
    resse
    -0.10
    -eyed
    -0.10
    é©·
    -0.09
    ulary
    -0.09
    anny
    -0.09
    arten
    -0.09
    ioneer
    -0.09
    åĶ§
    -0.09
    머
    -0.09
    POSITIVE LOGITS
    è¾Ī
    0.09
    ed
    0.09
    级åĪ«çļĦ
    0.09
    輩
    0.09
    agr
    0.09
    anse
    0.09
    è·º
    0.08
    æİıåĩº
    0.08
    ass
    0.08
    d
    0.08
    Activations Density 0.010%

    No Known Activations