© 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. 32046
    Prev
    Next
    INDEX
    Explanations

    fading and diminishing

    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
    ssel
    -0.10
    æ²½
    -0.09
    arti
    -0.09
    miss
    -0.09
    误åĮº
    -0.08
    ç¾¹
    -0.08
    æį©
    -0.08
    éĻ¶
    -0.08
    åĿļå®ŀçļĦ
    -0.08
    è´©åįĸ
    -0.08
    POSITIVE LOGITS
    ingly
    0.14
    æĺŁåħī
    0.10
    fully
    0.10
    ently
    0.10
    å·²ä¹ħçļĦ
    0.09
    æĹłå£°
    0.09
     dần
    0.09
    liest
    0.09
    ombat
    0.09
    ä¹ıåĬĽ
    0.09
    Activations Density 0.051%

    No Known Activations