© 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. 32413
    Prev
    Next
    INDEX
    Explanations

    feels like

    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
    neau
    -0.09
    fuse
    -0.09
    ales
    -0.09
    اÙĤ
    -0.09
    èĽĭ
    -0.09
    posed
    -0.08
    æ´İ
    -0.08
     dro
    -0.08
    ôt
    -0.08
    èĮµ
    -0.08
    POSITIVE LOGITS
    åĥıæĺ¯
    0.10
    å½ĵå±Ģ
    0.09
    ÑĥÑģÑĤ
    0.09
    æľīéĴĪ对æĢ§
    0.09
    -assets
    0.09
    иÑĪ
    0.08
    强è¡Į
    0.08
    ahir
    0.08
    ç¯ģ
    0.08
    çĶ¬
    0.08
    Activations Density 0.014%

    No Known Activations