© 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. 7109
    Prev
    Next
    INDEX
    Explanations

    chapter headings and numbers

    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
    æĭŃ
    -0.10
    LOOP
    -0.09
    éŃħ
    -0.08
    夺
    -0.08
    Loop
    -0.08
    èĻİ
    -0.08
    éĶIJ
    -0.07
    âĶIJ
    -0.07
    ioso
    -0.07
    ange
    -0.07
    POSITIVE LOGITS
    åİŁæĸĩ
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    åĭĺ
    0.09
    avad
    0.09
    è°ĭ
    0.09
    导读
    0.09
    ä½ľåĵģåĨħ容
    0.08
    æĵĺ
    0.08
    æīĵåį¡
    0.08
    utta
    0.08
    Activations Density 0.260%

    No Known Activations