© 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. 35694
    Prev
    Next
    INDEX
    Explanations

    communications systems

    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
    ourcing
    -0.10
    avers
    -0.09
    æİĸ
    -0.08
    inee
    -0.08
    å§ij
    -0.08
    对æīĭ
    -0.08
    åĸĤ
    -0.08
    黳
    -0.08
    innie
    -0.08
    éĢłè¡Ģ
    -0.08
    POSITIVE LOGITS
    èĥ¸æĢĢ
    0.10
    æ¹į
    0.09
    unication
    0.09
    çķħéĢļ
    0.09
    ipp
    0.09
    ë§Ŀ
    0.09
    reff
    0.09
    æ®Ĵ
    0.09
    éĢļ讯
    0.09
    Tower
    0.09
    Activations Density 0.071%

    No Known Activations