© 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. 32785
    Prev
    Next
    INDEX
    Explanations

    don't followed by a verb

    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
    ãģ£ãģįãĤĬ
    -0.11
    æĪijä¸Ģ缴
    -0.11
    _UNS
    -0.09
    rch
    -0.09
    ilk
    -0.09
    ãģĦãģŁãĤī
    -0.09
    éĺĹ
    -0.09
    ses
    -0.09
    _SU
    -0.09
    dt
    -0.09
    POSITIVE LOGITS
    aris
    0.10
    ibraries
    0.09
    egration
    0.09
    äºĭåĦ¿
    0.09
    宥
    0.08
    er
    0.08
    ers
    0.08
    aira
    0.08
     WINAPI
    0.08
    åħ¶æ¬¡æĺ¯
    0.08
    Activations Density 0.048%

    No Known Activations