© 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. 21447
    Prev
    Next
    INDEX
    Explanations

    inside of you

    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
    çĨŁ
    -0.10
    rimp
    -0.09
     __________________↵↵
    -0.09
    åľºä¸Ĭ
    -0.08
     Bren
    -0.08
    ils
    -0.08
    สล
    -0.08
     dev
    -0.08
    åĸĻ
    -0.08
    stro
    -0.08
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.13
    è´«åĽ°åľ°åĮº
    0.10
    åĨħåľ¨
    0.10
    æĬĬä»ĸ
    0.10
    å¾Īæ·±
    0.10
    ãģªãĤĬ
    0.10
    çįĴ
    0.10
    ä¹Łéļıä¹ĭ
    0.09
    åĨħå¿ĥçļĦ
    0.09
    æ¾İæ¹ĥ
    0.09
    Activations Density 0.032%

    No Known Activations