© 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. 4149
    Prev
    Next
    INDEX
    Explanations

    be verb + state/action

    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
    æĭĹ
    -0.10
    æŶèĬĤ
    -0.10
    æĪIJéķ¿ä¸º
    -0.10
    моÑĢ
    -0.09
    ä¹Łæĺ¯å¦ĤæѤ
    -0.09
    cec
    -0.09
    åłĤ
    -0.09
    PlainText
    -0.09
    oso
    -0.09
    croll
    -0.09
    POSITIVE LOGITS
    好äºĨ
    0.10
    abet
    0.10
    _parm
    0.09
    åĩºéŨ
    0.09
     forever
    0.09
    GLOSS
    0.08
    ãģ°
    0.08
    éĩijéĻµ
    0.08
    åĩºåľº
    0.08
    ç®ĹäºĨ
    0.08
    Activations Density 0.035%

    No Known Activations