© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 26848
    Prev
    Next
    INDEX
    Explanations

    Burren, spring, tulumensis, local-class, Lines starting

    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
    åĶĽ
    -0.09
    æ²¾
    -0.09
    庸
    -0.09
    imir
    -0.09
    _pdata
    -0.09
    /reference
    -0.09
     ÙĬÙĪÙĨ
    -0.09
    munition
    -0.08
    userdata
    -0.08
    ä¹ł
    -0.08
    POSITIVE LOGITS
    æ´ŀ
    0.13
    åľ°ä¸ĭ
    0.10
    羣åģĩ
    0.10
     formations
    0.10
     Formation
    0.10
    çŁ³çģ°
    0.09
    å½¢æĪIJ
    0.09
    çī¯
    0.09
    导游
    0.09
    Formation
    0.09
    Activations Density 0.057%

    No Known Activations