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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48686
    Prev
    Next
    INDEX
    Explanations

    stakeholders and related groups

    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
    º
    -0.10
    欢è¿İ大家
    -0.09
    çķ´
    -0.08
    åijµæĬ¤
    -0.08
    å´Ľ
    -0.08
    Ļ¨
    -0.08
    åĴĮåħ¶ä»ĸ
    -0.08
    ekyll
    -0.08
    oral
    -0.08
    ç¼Ĩ
    -0.08
    POSITIVE LOGITS
    hip
    0.13
    æѤäºĭ
    0.11
    ForResult
    0.09
    hips
    0.09
    åķ·
    0.09
    æѤ类
    0.09
    èle
    0.09
    amer
    0.09
    edImage
    0.09
    èĻij
    0.08
    Activations Density 0.007%

    No Known Activations