© 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. 9959
    Prev
    Next
    INDEX
    Explanations

    us or USA

    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
    æĽĻåħī
    -0.09
    MOTE
    -0.09
    ä¸ŃåĽ½ç»ıæµİ
    -0.09
    оÑģÑĤей
    -0.08
    ahir
    -0.08
    大çĪ·
    -0.08
    ä¸ĢæŶ
    -0.08
    jang
    -0.08
    让大家
    -0.08
    иде
    -0.08
    POSITIVE LOGITS
    ILITY
    0.10
    меÑĢ
    0.10
    enet
    0.10
    евиÑĩ
    0.09
    eful
    0.09
    è¿Ļç§įæĸ¹æ³ķ
    0.09
     Belmont
    0.09
    ller
    0.08
    amac
    0.08
    ä¸ĢæĬĬ
    0.08
    Activations Density 0.051%

    No Known Activations