© 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. 27310
    Prev
    Next
    INDEX
    Explanations

    consecutive or straight sequences

    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
    èĬ¹
    -0.10
    olf
    -0.09
    èĩ¾
    -0.09
    éľģ
    -0.09
     Rover
    -0.09
    .sap
    -0.09
    åĺĽ
    -0.09
    æ°¸ä¹ħ
    -0.09
     canon
    -0.08
     Bra
    -0.08
    POSITIVE LOGITS
    è¿ŀç»Ń
    0.20
     consecutive
    0.18
    éĢ£çºĮ
    0.16
     consect
    0.13
    æİ¥è¿ŀ
    0.13
     consec
    0.11
     kolej
    0.10
     hood
    0.10
    è¿ŀèĥľ
    0.09
    è¿ŀ
    0.09
    Activations Density 0.221%

    No Known Activations