© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51562
    Prev
    Next
    INDEX
    Explanations

    total or overall counts

    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
    çĭIJ
    -0.09
    æľīæĹ¶
    -0.09
    _AUX
    -0.09
    asan
    -0.09
    ession
    -0.09
    çĨĬ
    -0.08
    è°¨
    -0.08
    åĨĴ
    -0.08
    ager
    -0.08
    -dot
    -0.08
    POSITIVE LOGITS
    _EV
    0.10
    acet
    0.09
     Crate
    0.09
    妪
    0.09
    æ·±å¤Ħ
    0.09
    è¦ģ害
    0.08
    LocalizedString
    0.08
    åįģéĩĮ
    0.08
     Incredible
    0.08
    æ·¤
    0.08
    Activations Density 0.023%

    No Known Activations