© 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. 31727
    Prev
    Next
    INDEX
    Explanations

    reminded me of

    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
    éªļ
    -0.10
    æĸ¤
    -0.09
    át
    -0.08
    æīĭä¸ĭ
    -0.08
    ä¸į容æĺĵ
    -0.08
    eldon
    -0.08
    å®ĿçŁ³
    -0.08
    稳
    -0.08
    æŁ´
    -0.08
    羣æĥħ
    -0.08
    POSITIVE LOGITS
    æĥ³èµ·äºĨ
    0.20
    æĥ³èµ·
    0.17
    æĥ³åĪ°äºĨ
    0.15
     reminded
    0.15
    æĥ³åĪ°
    0.14
     reminds
    0.13
    ä¼¼
    0.13
    èģĶæĥ³
    0.13
     reminiscent
    0.12
     remind
    0.12
    Activations Density 0.030%

    No Known Activations