© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1547
    Prev
    Next
    INDEX
    Explanations

    programming constructs with methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    è¶ĬæĿ¥è¶Ĭé«ĺ
    -0.26
    _PD
    -0.25
    ä¼ļ计å¸Ī
    -0.25
    Disclosure
    -0.24
    abr
    -0.23
    è¶ĬæĿ¥è¶Ĭ好
    -0.23
     PD
    -0.22
    SDK
    -0.22
    (KP
    -0.21
    brid
    -0.21
    POSITIVE LOGITS
    ugu
    0.24
     unnamed
    0.23
     siblings
    0.23
    åİŁå§ĭ
    0.23
    #__
    0.23
     multiplication
    0.23
    åĪĩ
    0.23
     hints
    0.23
    çļĦ
    0.22
     ::=
    0.22
    Activations Density 0.657%

    No Known Activations