© 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. 2359
    Prev
    Next
    INDEX
    Explanations

    children and grandchildren

    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
    为æ°ij
    -0.10
    马
    -0.10
    mary
    -0.10
    å§IJå§IJ
    -0.09
    æ´ĹèĦ¸
    -0.09
    ç±³åħ°
    -0.09
    åIJ¯èĴĻ
    -0.09
    åĬ¡
    -0.09
    è¿ĺä¸įå¦Ĥ
    -0.09
    irl
    -0.08
    POSITIVE LOGITS
     grandchildren
    0.15
    åŃĻåŃIJ
    0.14
    åIJİ代
    0.12
    ä¾Ħ
    0.12
     grandson
    0.11
    åŃ«
    0.11
    åŃIJåŃĻ
    0.11
    åŃĻ
    0.11
     granddaughter
    0.11
    sons
    0.11
    Activations Density 0.060%

    No Known Activations