© 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. 17733
    Prev
    Next
    INDEX
    Explanations

    myself/yourself

    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
    帮æĪij
    -0.09
    _RF
    -0.08
    åħ·
    -0.08
    elman
    -0.08
    宿
    -0.08
    æīĭå¥Ĺ
    -0.08
    æIJĵ
    -0.08
     RF
    -0.08
    ova
    -0.08
     Chronicle
    -0.08
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.10
    éĬ®
    0.09
    åį³æŶ
    0.09
    æ¾Ī
    0.09
    _phys
    0.09
    llx
    0.09
    stice
    0.09
    身å¤Ħ
    0.08
    èĬĤæĹ¥
    0.08
    为èĩªå·±
    0.08
    Activations Density 0.026%

    No Known Activations