© 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. 21481
    Prev
    Next
    INDEX
    Explanations

    moderate to severe

    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
    ç£ķ
    -0.10
    ialis
    -0.09
    äººæł¼
    -0.09
    æijĺè¦ģ
    -0.09
    stag
    -0.09
    UDO
    -0.09
    åĴĮå°ļ
    -0.09
    umas
    -0.08
    wor
    -0.08
    å¹²æī°
    -0.08
    POSITIVE LOGITS
    ness
    0.09
    æ¶Ĥ
    0.09
    çģ«åĬĽ
    0.08
    oy
    0.08
    ish
    0.08
    ãģ¾ãģĹãģ¦
    0.08
    Viet
    0.08
    æ¿¡
    0.08
    ly
    0.08
    éģĤ
    0.08
    Activations Density 0.001%

    No Known Activations