© 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. 37371
    Prev
    Next
    INDEX
    Explanations

    Hollywood, photos, .net

    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
    åĩºå¤Ħ
    -0.10
    çĬ¶åĨµ
    -0.09
    èĻĵ
    -0.09
    ivor
    -0.09
    Marshal
    -0.09
    isia
    -0.08
    _DISPATCH
    -0.08
    ária
    -0.08
    çĵ®
    -0.08
    MapView
    -0.08
    POSITIVE LOGITS
    äºĨ许å¤ļ
    0.10
    ught
    0.09
    éľīç´ł
    0.09
    itude
    0.09
    妹åŃIJ
    0.08
    äºĨäºĽ
    0.08
    äºĨä»ĸçļĦ
    0.08
    fir
    0.08
    ulous
    0.08
    êµŃ
    0.08
    Activations Density 0.003%

    No Known Activations