© 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. 4724
    Prev
    Next
    INDEX
    Explanations

    Jennifer Lauren Independence Million CT

    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
    èĢģ人家
    -0.09
     Ga
    -0.09
    çĤĢ
    -0.08
    колÑĮ
    -0.08
    thetic
    -0.08
    ãģ¹ãģį
    -0.08
    åĪ«äººçļĦ
    -0.08
     ga
    -0.08
     Garmin
    -0.08
    橦
    -0.08
    POSITIVE LOGITS
    çĴĢ
    0.09
    _dictionary
    0.09
    åĺ»
    0.08
    ãģ®å¤§
    0.08
     ев
    0.08
    .Ret
    0.08
    票价
    0.08
    _Debug
    0.08
    sb
    0.08
    åĴ§
    0.08
    Activations Density 0.009%

    No Known Activations