© 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. 31676
    Prev
    Next
    INDEX
    Explanations

    food and drink

    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
    åºŁæŧ
    -0.10
    åĨħåľ°
    -0.09
    ä¸ĢåĪĨéĴ±
    -0.09
    prs
    -0.09
    é£İåIJ¹
    -0.08
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.08
    enen
    -0.08
    uster
    -0.08
    æĻŁ
    -0.08
    eya
    -0.08
    POSITIVE LOGITS
    åĴĮæľįåĬ¡
    0.10
    æĢ»çĽij
    0.10
    isel
    0.10
    mPid
    0.09
    _die
    0.09
    éĩĮç¨ĭ
    0.09
    ie
    0.09
    afone
    0.09
     mover
    0.08
    OptionsResolver
    0.08
    Activations Density 0.022%

    No Known Activations