© 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. 22811
    Prev
    Next
    INDEX
    Explanations

    trimming or cutting something

    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
    æŁIJç§į
    -0.11
    aten
    -0.10
    aven
    -0.10
    è¦ļ
    -0.09
    æĭį
    -0.09
    æ·±åĪĩ
    -0.09
    atings
    -0.09
    anker
    -0.09
    osity
    -0.08
     Crushers
    -0.08
    POSITIVE LOGITS
     Tale
    0.08
    cant
    0.08
    othy
    0.08
    é«Ń
    0.08
    åıijçİ°éĹ®é¢ĺ
    0.08
    -edge
    0.08
     retr
    0.08
    èĢĥæħ®
    0.08
     Tales
    0.08
    èĶĵ
    0.08
    Activations Density 0.017%

    No Known Activations