© 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. 56067
    Prev
    Next
    INDEX
    Explanations

    more than / longer than

    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
    endar
    -0.10
    å°Ĭ
    -0.10
    åŃĺåľ¨éĹ®é¢ĺ
    -0.09
    éķĮ
    -0.09
     naw
    -0.09
    èĥ½åģļåĪ°
    -0.09
    çĺĻ
    -0.09
    aland
    -0.08
    æ´ĹèĦ¸
    -0.08
    ÑĢеÑģÑĤ
    -0.08
    POSITIVE LOGITS
    minate
    0.09
    åºŁè¯Ŀ
    0.09
    篦
    0.09
    é¢Ŀå¤ĸ
    0.08
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.08
    preload
    0.08
    _UUID
    0.08
    thes
    0.08
    æ»ł
    0.08
    éĢģä¸Ĭ
    0.08
    Activations Density 0.001%

    No Known Activations