© 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. 8100
    Prev
    Next
    INDEX
    Explanations

    taxpayer funded

    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
    åİŁåĽłä¹ĭä¸Ģ
    -0.09
    åħļç»Ħç»ĩ
    -0.09
     costa
    -0.09
    _defs
    -0.09
    çĶŁäº§èĥ½åĬĽ
    -0.09
    å²Ĺ
    -0.09
    èĨĽ
    -0.08
    æ²īéĩį
    -0.08
    urbed
    -0.08
    _DM
    -0.08
    POSITIVE LOGITS
    åĨ¥
    0.10
    èıģ
    0.09
    èĪģ
    0.09
    åĵº
    0.09
     пÑĢедназнаÑĩен
    0.08
    rine
    0.08
    ften
    0.08
    åĭĻ
    0.08
    alia
    0.08
    liers
    0.08
    Activations Density 0.009%

    No Known Activations