© 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. 38620
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
    åĪ¸
    -0.10
    è¶Ł
    -0.09
    两次
    -0.09
     RH
    -0.09
    pname
    -0.09
    eah
    -0.09
    éĿĴèĽĻ
    -0.09
    ENA
    -0.09
    ÑĭÑĤа
    -0.08
    RF
    -0.08
    POSITIVE LOGITS
    åı·çłģ
    0.11
    ç°ĩ
    0.09
    éĵ®
    0.09
    èĻŁ
    0.09
    å«ī
    0.08
    çĶ¨äºİ
    0.08
    imore
    0.08
    ä¸ĵçĶ¨
    0.08
    .dispatchEvent
    0.08
    åĵį
    0.08
    Activations Density 0.119%

    No Known Activations