© 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. 32278
    Prev
    Next
    INDEX
    Explanations

    outside or exterior

    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
    åĨħåľ¨
    -0.09
    uts
    -0.09
    æ°ijå¿ĥ
    -0.08
    è¦ģ害
    -0.08
    主è¦ģåĨħ容
    -0.08
    åĪĩãĤĮ
    -0.08
    åĨħç§ij
    -0.08
    äºĮæĪĺ
    -0.08
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    çݰ代社ä¼ļ
    -0.08
    POSITIVE LOGITS
    ¢
    0.10
    éĥĽ
    0.09
    reb
    0.09
     Kahn
    0.09
    涯
    0.09
    ipated
    0.08
    reme
    0.08
    ervation
    0.08
    most
    0.08
    تض
    0.08
    Activations Density 0.044%

    No Known Activations