© 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. 1531
    Prev
    Next
    INDEX
    Explanations

    implications, pending, discussion, briefing

    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
     even
    -0.31
     unle
    -0.30
     ideal
    -0.29
    çĶļèĩ³
    -0.29
     tháºŃm
    -0.27
    çIJĨæĥ³
    -0.27
    å·ħå³°
    -0.27
    _even
    -0.27
    çĶļèĩ³æĺ¯
    -0.27
     paradox
    -0.26
    POSITIVE LOGITS
    è®®é¢ĺ
    0.40
    审议
    0.39
     pending
    0.38
    é¢ĦåijĬ
    0.36
    ä¾ĭè¡Į
    0.36
    修订
    0.34
    äºĭ项
    0.34
     briefing
    0.34
     discussion
    0.34
    è®®æ¡Ī
    0.34
    Activations Density 0.041%

    No Known Activations