© 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. 54053
    Prev
    Next
    INDEX
    Explanations

    initialisms followed by numbers/words

    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
    ãģĵãģ¨
    -0.11
    çĨ
    -0.11
     Dud
    -0.10
    AIT
    -0.10
    åĴ¬
    -0.10
    æ»Ĥ
    -0.10
    社ä¼ļåĮĸ
    -0.09
    çĥĪ
    -0.09
    ackson
    -0.09
    çħĮ
    -0.09
    POSITIVE LOGITS
    ummings
    0.09
    rawl
    0.09
    aching
    0.09
    ortex
    0.09
    ymb
    0.09
    rypt
    0.09
    rossover
    0.09
    缨
    0.09
    enary
    0.09
    失è°ĥ
    0.09
    Activations Density 0.195%

    No Known Activations