© 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. 56690
    Prev
    Next
    INDEX
    Explanations

    stock, quarterly, consecutive, Is

    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
    缸å¤Ħ
    -0.09
    nel
    -0.09
     forwarding
    -0.08
     Stard
    -0.08
     vat
    -0.08
    abox
    -0.08
    antz
    -0.08
    å¾Īä½İ
    -0.08
    anton
    -0.08
    onces
    -0.08
    POSITIVE LOGITS
    åĽŀè´Ń
    0.12
    åĽŀæĿ¥
    0.10
    åĸĨ
    0.10
    羣çĪ±
    0.09
    enia
    0.09
    è§ĦèĮĥåĮĸ
    0.09
    AAP
    0.09
    æ¼ĵ
    0.09
    à¸ķล
    0.08
    åħ°èĬ±
    0.08
    Activations Density 0.021%

    No Known Activations