© 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. 11700
    Prev
    Next
    INDEX
    Explanations

    stock price percentage changes

    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
    agna
    -0.09
    çĤ½
    -0.09
    éĿ©
    -0.08
    é¹°
    -0.08
    icy
    -0.08
    ild
    -0.08
    rie
    -0.08
    éĢĬ
    -0.08
    ä¸ĸçķĮè§Ĥ
    -0.08
     ~=
    -0.08
    POSITIVE LOGITS
    å¹ħ度
    0.11
    è·Įå¹ħ
    0.10
    骤
    0.10
    ä¸Ģå¤ľ
    0.10
    leton
    0.09
    æĭ¦
    0.09
    æ·±å¤ľ
    0.09
    åIJĪä½ľä¼Ļä¼´
    0.08
    è·Łéļı
    0.08
    塾
    0.08
    Activations Density 0.026%

    No Known Activations