© 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. 7877
    Prev
    Next
    INDEX
    Explanations

    content publication and status

    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
    åĪĽæĸ°
    -0.10
    .foreach
    -0.09
    åĸ°
    -0.09
    èµĽ
    -0.09
    èµĽåIJİ
    -0.08
    tog
    -0.08
    åĪĽæĸ°åıijå±ķ
    -0.08
     Rum
    -0.08
    çļĦç¾İ好
    -0.08
    åĪĽæĸ°é©±åĬ¨
    -0.08
    POSITIVE LOGITS
    对å¤ĸ
    0.12
    åĪ®
    0.09
    èĦĨ
    0.09
     Acres
    0.09
    _EXTERN
    0.09
    taire
    0.09
    etu
    0.09
    ModelIndex
    0.09
    è¿Ļ两个
    0.08
    饱
    0.08
    Activations Density 0.004%

    No Known Activations