© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20506
    Prev
    Next
    INDEX
    Explanations

    passive

    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
    çģ¼
    -0.10
    çĤĴä½ľ
    -0.10
    æķıæį·
    -0.09
    apus
    -0.09
    æĬĢæ³ķ
    -0.09
    гоÑĢ
    -0.09
    èĿ®
    -0.09
    åĴĮåľ°åĮº
    -0.09
    chin
    -0.09
    çļĦåĪ©çĽĬ
    -0.09
    POSITIVE LOGITS
    被åĬ¨
    0.24
     passive
    0.19
     Passive
    0.17
     pass
    0.13
    /pass
    0.10
    (pass
    0.10
    æ¶Īæŀģ
    0.09
    åıĹãģij
    0.08
     kok
    0.08
     coast
    0.08
    Activations Density 0.028%

    No Known Activations