© 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. 31053
    Prev
    Next
    INDEX
    Explanations

    life and time related situations

    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
    èµŀèµı
    -0.08
    å°ıå·§
    -0.08
    å¯¹æľªæĿ¥
    -0.08
    çĶ·å¥³
    -0.08
    æ¸ł
    -0.08
    æľ¦èĥ§
    -0.08
    对ä¸ŃåĽ½
    -0.07
    æİĴéĺŁ
    -0.07
    æī«ä¸Ģæī«
    -0.07
    iy
    -0.07
    POSITIVE LOGITS
    prep
    0.10
    agher
    0.10
     prep
    0.09
    åį³å°Ĩ
    0.09
    izon
    0.09
    óa
    0.09
    orns
    0.09
    inged
    0.08
    remium
    0.08
    naire
    0.08
    Activations Density 1.554%

    No Known Activations