© 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. 1796
    Prev
    Next
    INDEX
    Explanations

    Leh, Leia, Lew, Lehtmatsa

    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
    eer
    -0.12
    åŃ¦å®¶
    -0.10
    ities
    -0.10
    idad
    -0.09
     зн
    -0.09
    ìĺģ
    -0.09
    .sharedInstance
    -0.09
    оз
    -0.08
     cánh
    -0.08
    izr
    -0.08
    POSITIVE LOGITS
    ëŁī
    0.12
    roit
    0.10
    éĿ¢çĻ½
    0.10
    ¤í
    0.09
    lit
    0.09
    ilton
    0.09
    оÑĢ
    0.09
    l
    0.09
    éļIJ约
    0.09
    itag
    0.09
    Activations Density 0.010%

    No Known Activations