© 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. 32911
    Prev
    Next
    INDEX
    Explanations

    money amounts

    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
    æ±°
    -0.10
    ç±´
    -0.10
    åįģæĿ¡
    -0.10
    ä»ĺè´¹
    -0.09
    åĪ©äºļ
    -0.09
    åIJ¬è¯¾
    -0.09
    éķľåŃIJ
    -0.09
    æ·ĺ
    -0.09
    æ³Ķ
    -0.08
    é¹Ĥ
    -0.08
    POSITIVE LOGITS
    è¶ħé«ĺ
    0.09
    çĻ¾ä¸ĩ
    0.09
    管çIJĨå±Ģ
    0.09
    å¸Ĥåİ¿
    0.09
    èĢĢçľ¼
    0.09
    åħ±äº«
    0.08
    ocr
    0.08
    ajs
    0.08
    åħ¬åħ±æľįåĬ¡
    0.08
    åĪĨåī²
    0.08
    Activations Density 0.010%

    No Known Activations