© 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. 5650
    Prev
    Next
    INDEX
    Explanations

    mobile network generations

    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
    çĨ¨
    -0.09
    èĶļ
    -0.09
    vern
    -0.09
    MSN
    -0.09
    asher
    -0.09
    åħ³æ³¨
    -0.08
    ificant
    -0.08
     trib
    -0.08
    ä»İä¸ļ
    -0.08
    梦è§ģ
    -0.08
    POSITIVE LOGITS
    æ¼Ķ
    0.09
    æĻºæħ§åŁİå¸Ĥ
    0.08
    è¿Ļå¼ł
    0.08
    客æ°Ķ
    0.08
     Rooney
    0.08
    çĸ¥
    0.08
    驸
    0.08
    é¢Ħ订
    0.08
    åŁºç«Ļ
    0.08
    æľ«
    0.08
    Activations Density 0.063%

    No Known Activations