© 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. 48606
    Prev
    Next
    INDEX
    Explanations

    run

    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
    erne
    -0.09
    _OM
    -0.09
    èĿ¶
    -0.09
    ctxt
    -0.09
    üst
    -0.09
    >Loading
    -0.09
    бил
    -0.09
    /chart
    -0.09
    _GP
    -0.08
    æű
    -0.08
    POSITIVE LOGITS
    ped
    0.10
    çĹħæĪ¿
    0.09
    åħ¬çĽĬæ´»åĬ¨
    0.09
    ç»ļ
    0.08
    gers
    0.08
    apo
    0.08
    uil
    0.08
    æķ£å¸ĥ
    0.08
    æIJ
    0.08
     affairs
    0.08
    Activations Density 0.039%

    No Known Activations