© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37292
    Prev
    Next
    INDEX
    Explanations

    public offering process

    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
    nox
    -0.09
    abet
    -0.08
    dek
    -0.08
    eteor
    -0.08
    ÑĤин
    -0.08
    墨
    -0.08
    åľ°æ®µ
    -0.08
    æĪį
    -0.08
     installation
    -0.08
     Pit
    -0.08
    POSITIVE LOGITS
    çĶ¨èį¯
    0.13
    èį¯çī©
    0.13
    åĪ¶èį¯
    0.12
    åĪ¶åīĤ
    0.11
    èį¯ä¸ļ
    0.11
    ç§ijçłĶ
    0.11
    èį¯åĵģ
    0.11
    FDA
    0.11
    Drug
    0.11
    drug
    0.10
    Activations Density 0.219%

    No Known Activations