© 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. 52423
    Prev
    Next
    INDEX
    Explanations

    growing up

    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
    jee
    -0.10
    oman
    -0.10
    æĸ°çĶŁ
    -0.09
    æĸ°å»º
    -0.09
    eeper
    -0.09
     Gaw
    -0.09
    egin
    -0.09
    åŁ
    -0.08
    AMS
    -0.08
    IEW
    -0.08
    POSITIVE LOGITS
    éŀĭ
    0.09
    _IDX
    0.08
    åĥı个
    0.08
    orus
    0.08
     ÑĤÑĢÑĥд
    0.08
    isin
    0.08
    主人åħ¬
    0.08
    imore
    0.08
    roof
    0.08
    éĴ¿
    0.08
    Activations Density 0.153%

    No Known Activations