© 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. 56391
    Prev
    Next
    INDEX
    Explanations

    molds and moulding

    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
    uto
    -0.09
    æī¬
    -0.08
    puter
    -0.08
    abb
    -0.08
    åľ°æ¯¯
    -0.08
    èĤ¤
    -0.08
    å¼Ľ
    -0.08
    ä»ĭ
    -0.08
    åĤį
    -0.08
    ena
    -0.08
    POSITIVE LOGITS
    å¥Ĺè£ħ
    0.09
    模åħ·
    0.09
    ç»Ģ
    0.09
    èģĶéĢļ
    0.09
    ä¿£
    0.09
     Pace
    0.09
    çĸı导
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    说æĪij
    0.09
    åĬŀ好
    0.09
    Activations Density 0.161%

    No Known Activations