© 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. 4845
    Prev
    Next
    INDEX
    Explanations

    roundedflatareas

    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
    å³Ĵ
    -0.09
    éĺ³åİ¿
    -0.09
    çĶ¨çĶµ
    -0.09
    .datasource
    -0.08
    è£ħå¤ĩåĪ¶éĢł
    -0.08
    æĥĬåı¹
    -0.08
    è¶ħé¢Ŀ
    -0.08
    è¿ľæĸ¹
    -0.08
    ä¸īå±Ĥ
    -0.08
    åģ¶
    -0.08
    POSITIVE LOGITS
    ç¼ĺ
    0.10
    ä»İåīį
    0.09
    issan
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    æĺ¾éľ²
    0.09
    强æľīåĬĽçļĦ
    0.09
    ç·£
    0.09
     apex
    0.09
    åĪĩåħ¥
    0.09
    SCR
    0.08
    Activations Density 0.377%

    No Known Activations