© 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. 37957
    Prev
    Next
    INDEX
    Explanations

    vapor states or phase

    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
    æĿ¥çĶµ
    -0.09
    趣åij³
    -0.08
    venue
    -0.08
    é²ľ
    -0.08
    ä¸ĬéŨ
    -0.08
    opia
    -0.08
    iming
    -0.08
    pit
    -0.08
    athers
    -0.08
    ellow
    -0.08
    POSITIVE LOGITS
    æħĭ
    0.10
    弥漫
    0.10
    纸ä¸Ĭ
    0.09
    çĺ¾
    0.09
    åĽŀæĥ³
    0.09
    å±ĭéĩĮ
    0.09
    ç¥Ģ
    0.09
    æ±¹
    0.09
    空ä¸Ń
    0.09
    æľīæĽ´å¥½çļĦ
    0.09
    Activations Density 0.040%

    No Known Activations