© 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. 63351
    Prev
    Next
    INDEX
    Explanations

    certified

    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
    оÑģÑĮ
    -0.11
    ertest
    -0.09
    åİĿ
    -0.09
    aroo
    -0.09
    Ñģал
    -0.09
    ertools
    -0.09
    cco
    -0.09
    nish
    -0.09
    iness
    -0.08
    orra
    -0.08
    POSITIVE LOGITS
    ainty
    0.13
    ificates
    0.13
    ิà¸ķ
    0.10
    çĺķ
    0.09
     занÑıÑĤ
    0.09
    inking
    0.09
    ainties
    0.09
     каÑĩеÑģÑĤва
    0.09
    IFICATE
    0.09
    çijķ
    0.09
    Activations Density 0.034%

    No Known Activations