© 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. 38061
    Prev
    Next
    INDEX
    Explanations

    private companies, investment

    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
    chal
    -0.10
    è¶ħé¢Ŀ
    -0.09
    éĢĽ
    -0.09
    宿
    -0.09
    çĻ¾åĪĨçĻ¾
    -0.09
    accom
    -0.09
    icker
    -0.08
    çĶŁçī©åѦ
    -0.08
    ç½ijé¦ĸ页
    -0.08
    AGE
    -0.08
    POSITIVE LOGITS
    cold
    0.10
    uart
    0.09
    åĿİ
    0.09
    æ¦ľ
    0.09
    满åĪĨ
    0.08
     blanks
    0.08
    åĩ¸
    0.08
    åŁºåĩĨ
    0.08
    å¦ĤæĦı
    0.08
     Patton
    0.08
    Activations Density 0.027%

    No Known Activations