© 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. 58471
    Prev
    Next
    INDEX
    Explanations

    grassroots and community-based movements

    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
    thing
    -0.11
    à¹Ħว
    -0.09
    åįļ士åѦä½į
    -0.09
    tt
    -0.08
    åıijè¾¾åĽ½å®¶
    -0.08
    æĹłå½¢
    -0.08
    CustomAttributes
    -0.08
    éĹªçĥģ
    -0.08
    åĩ»
    -0.08
    è¾ħ
    -0.08
    POSITIVE LOGITS
    åĬĽéĩı
    0.13
    ìłģìľ¼ë¡ľ
    0.10
    åıŁ
    0.10
     unins
    0.10
    nik
    0.10
    HEN
    0.10
     efforts
    0.09
    åĮĨ
    0.09
    åŬ
    0.09
    åŁºå±Ĥ
    0.09
    Activations Density 0.004%

    No Known Activations