© 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. 23010
    Prev
    Next
    INDEX
    Explanations

    exam cram

    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
    èī¯
    -0.09
     orm
    -0.09
    ipt
    -0.09
     Hazel
    -0.08
    æĹ¶ä»£çļĦ
    -0.08
    decess
    -0.08
    åĬŁå¤«
    -0.08
    äºĨä¸Ģä¸ĭ
    -0.08
    è¡¿
    -0.08
    娣
    -0.08
    POSITIVE LOGITS
    emu
    0.11
    .Sdk
    0.10
    åħ¸
    0.09
    ä¸įæĪIJ
    0.09
    oks
    0.09
    æŃ£åĵģ
    0.09
    çļĦ帮åĬ©
    0.08
    å½ĵå±Ģ
    0.08
    çļĦ羣å®ŀ
    0.08
     Adventures
    0.08
    Activations Density 0.036%

    No Known Activations