© 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. 34006
    Prev
    Next
    INDEX
    Explanations

    song 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
    å²Į
    -0.09
    æĪŁ
    -0.09
    å²ĺ
    -0.09
     Fucking
    -0.09
    >null
    -0.09
     Rubio
    -0.09
    çĨ¹
    -0.09
    éļ°
    -0.09
     tits
    -0.08
    å²³
    -0.08
    POSITIVE LOGITS
    ä¸ĩéĩĮ
    0.09
    spd
    0.09
    inkel
    0.09
    Pipeline
    0.08
    æīĬ
    0.08
     UIL
    0.08
    imageUrl
    0.08
    Telegram
    0.08
    轻轻
    0.08
    ç»ıèIJ¥ç®¡çIJĨ
    0.08
    Activations Density 0.103%

    No Known Activations