© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53304
    Prev
    Next
    INDEX
    Explanations

    wide-rangingcommon senseforward-thinkingmean scenes

    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
    å¼Ģåĩº
    -0.11
    èı±
    -0.11
    ors
    -0.10
    éĹ¯
    -0.10
     Bottle
    -0.09
    å°ıçĻ½
    -0.09
    Ħ件
    -0.09
    çĵ¶é¢Ī
    -0.09
    ARAM
    -0.09
    æĶĢçĻ»
    -0.09
    POSITIVE LOGITS
    -minded
    0.12
     minded
    0.11
    æĺŁè¾°
    0.09
    çĥ¦
    0.09
    -hearted
    0.08
     mind
    0.08
    èĦijåŃIJ
    0.08
    -headed
    0.08
    çĮ·
    0.08
     mang
    0.08
    Activations Density 0.050%

    No Known Activations