© 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. 55318
    Prev
    Next
    INDEX
    Explanations

    lack of awareness or knowledge

    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
    çĨŁæĤī
    -0.10
    çľĭåĩº
    -0.10
    æĽ´èĥ½
    -0.10
    æĩĤå¾Ĺ
    -0.10
    åį°è±¡æ·±åĪ»
    -0.09
    çĨŁæĤīçļĦ
    -0.09
    ä¸įçĶ±
    -0.09
    çĨŁ
    -0.09
    æ¢Ń
    -0.09
    ç²¾çĽĬæ±Ĥç²¾
    -0.09
    POSITIVE LOGITS
    gar
    0.09
    éo
    0.08
    angi
    0.08
    곤
    0.08
     Jog
    0.08
    ừng
    0.08
    èİ·
    0.08
    amar
    0.08
    (ang
    0.08
    å®ĩ
    0.08
    Activations Density 0.058%

    No Known Activations