© 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. 38918
    Prev
    Next
    INDEX
    Explanations

    coat types, girth, thick insulation

    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
    seo
    -0.08
    apist
    -0.08
     единÑģÑĤв
    -0.08
    DLL
    -0.08
    -pills
    -0.08
    uell
    -0.08
    ủ
    -0.08
    emo
    -0.08
    åIJİå¤ĩ
    -0.08
    åĩĨ
    -0.08
    POSITIVE LOGITS
    åĪĪ
    0.11
    åĪĨ红
    0.09
    èĪĴéĢĤçļĦ
    0.09
    çĿĩ
    0.09
    åºŃ审
    0.09
    åĿİ
    0.09
    èĭ«
    0.09
    åıĸæļĸ
    0.09
    è®®ä¼ļ
    0.09
    ä¸İæĹ¶ä¿±è¿Ľ
    0.09
    Activations Density 0.030%

    No Known Activations