© 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. 23100
    Prev
    Next
    INDEX
    Explanations

    support for

    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
    OMIC
    -0.11
     инÑĦоÑĢм
    -0.10
    åİ¢
    -0.09
    çĶµåŃIJ产åĵģ
    -0.09
    æĹ·
    -0.09
    示èĮĥ
    -0.09
    åĵĪåĪ©
    -0.09
    亮
    -0.09
    ä¹ĭ声
    -0.08
     trÆ°á»Łng
    -0.08
    POSITIVE LOGITS
    æĶ¯æĮģ
    0.16
     support
    0.16
    support
    0.12
     Support
    0.12
    Support
    0.12
    _support
    0.12
     Unterstützung
    0.12
    _SUPPORT
    0.11
    æĶ¯æĮģåĬĽåº¦
    0.11
    -support
    0.11
    Activations Density 0.204%

    No Known Activations