© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8398
    Prev
    Next
    INDEX
    Explanations

    event

    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
    æĦıåij³
    -0.10
    hood
    -0.09
    Powered
    -0.09
    åѦåīįæķĻèĤ²
    -0.09
    xon
    -0.09
     gib
    -0.08
    å³Ħ
    -0.08
     Crunch
    -0.08
    常å§Ķ
    -0.08
    horn
    -0.08
    POSITIVE LOGITS
    uality
    0.10
    ummies
    0.10
    è§Ħç¨ĭ
    0.09
    çŃ¹
    0.09
    åľºåIJĪ
    0.08
    人次
    0.08
    à¹īà¸Ńย
    0.08
    .synthetic
    0.08
    orris
    0.08
    ekt
    0.08
    Activations Density 0.022%

    No Known Activations