© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20211
    Prev
    Next
    INDEX
    Explanations

    lists of actions or states

    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
    ENDING
    -0.10
    _ENCODING
    -0.10
    缮åīįæŃ£åľ¨
    -0.09
    opr
    -0.09
    æĿª
    -0.09
    å¸IJåı·
    -0.09
    åħķ
    -0.09
    ÙģÙĪر
    -0.08
    marsh
    -0.08
    .mit
    -0.08
    POSITIVE LOGITS
     being
    0.18
    being
    0.14
     having
    0.12
     sendo
    0.12
     étant
    0.11
    Being
    0.10
     Being
    0.10
     вÑĭпол
    0.09
     siendo
    0.09
    横
    0.09
    Activations Density 0.508%

    No Known Activations