© 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. 55158
    Prev
    Next
    INDEX
    Explanations

    cost and financial loss

    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
    å¼ķçĪĨ
    -0.09
    acre
    -0.09
    çĶ©
    -0.09
    æĭĪ
    -0.09
    gear
    -0.09
     defin
    -0.09
    å´Ľ
    -0.09
    _lua
    -0.09
    èĩªç§°
    -0.09
    è¿Ľå±ķæĥħåĨµ
    -0.08
    POSITIVE LOGITS
    失åİ»äºĨ
    0.10
     lost
    0.10
    åĨįä¹Ł
    0.10
     loss
    0.09
     Loss
    0.09
    å®Ŀè´µ
    0.08
    åĨ¤
    0.08
     posted
    0.08
    å®ŀå®ŀåľ¨åľ¨
    0.08
     поÑĤеÑĢ
    0.08
    Activations Density 0.093%

    No Known Activations