© 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. 35687
    Prev
    Next
    INDEX
    Explanations

    moisture loss and retention

    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
    æijĩ头
    -0.09
    åįĵ
    -0.08
    ereal
    -0.08
    /thumb
    -0.08
    ä¸ĩ人次
    -0.08
    ORED
    -0.08
    ниÑĨ
    -0.08
    ibility
    -0.08
    _BUF
    -0.08
    ethyst
    -0.08
    POSITIVE LOGITS
    ä¿Ŀ温
    0.12
    ä¿Ŀæļĸ
    0.11
    è¿Ļä¸ĢçĤ¹
    0.09
    å¾ħéģĩ
    0.09
    è¿ĻçĤ¹
    0.09
    éİĸ
    0.09
    _pres
    0.09
    éĶģ
    0.09
    çķĻåŃĺ
    0.09
    æľªæĪIJ
    0.09
    Activations Density 0.024%

    No Known Activations