© 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. 33228
    Prev
    Next
    INDEX
    Explanations

    appointment to this

    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
    IM
    -0.09
    åİŁæľīçļĦ
    -0.08
    oke
    -0.08
    åħĪ天
    -0.08
    è¿Ļä¸Ģå¹´
    -0.08
    åľ¨è¿ĩ渡
    -0.07
    天çĦ¶
    -0.07
    æĹ¢åı¯ä»¥
    -0.07
     IM
    -0.07
     grips
    -0.07
    POSITIVE LOGITS
    æĪIJæŀľ
    0.11
    æĪIJåŀĭ
    0.10
    æĪIJéķ¿
    0.10
    æĪIJéķ·
    0.10
    anje
    0.10
    çļĦæĪIJéķ¿
    0.10
    åıijå±ķ壮大
    0.10
    åĬŁåĬ³
    0.10
    äºĮæīĭ
    0.09
    licit
    0.09
    Activations Density 0.073%

    No Known Activations