© 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. 39688
    Prev
    Next
    INDEX
    Explanations

    age or years following names

    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
    æĸ½å±ķ
    -0.10
    沿çĿĢ
    -0.09
    Impl
    -0.09
    æ¯ĶåĪ©
    -0.08
    碰
    -0.08
    ãĥŃãĥ¼
    -0.08
    çĵĴ
    -0.08
    à®±
    -0.08
    èĥİ
    -0.08
    ç½ķ
    -0.08
    POSITIVE LOGITS
    å¹´é¾Ħ
    0.17
    年纪
    0.16
     aged
    0.16
     age
    0.14
     tuá»ķi
    0.14
    å¹´è½»
    0.13
    _age
    0.13
    é¾Ħ
    0.13
    (age
    0.13
    å¹´é¾Ħ段
    0.13
    Activations Density 0.234%

    No Known Activations