© 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. 62678
    Prev
    Next
    INDEX
    Explanations

    statistical tests and modelling

    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
    éĽħ
    -0.09
    çĶŁçĹħ
    -0.09
    PLICATION
    -0.08
    使åħ¶
    -0.08
    级
    -0.08
     NotImplemented
    -0.08
    çĺ¾
    -0.08
    beh
    -0.08
    ç»ıåİĨ
    -0.08
    çİ°æľī
    -0.08
    POSITIVE LOGITS
    æĶ¹èī¯
    0.10
    è¿Ļæĺ¯ä¸Ģç§į
    0.10
    ä¸ĢçĤ¹
    0.10
     method
    0.09
    andles
    0.09
    åĬ¨
    0.09
    继
    0.09
    æ°´è´¨
    0.09
    _DSP
    0.09
    åĪĽä¼¤
    0.09
    Activations Density 0.457%

    No Known Activations