© 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. 4569
    Prev
    Next
    INDEX
    Explanations

    natural landscapes, wildlife, and exotic places

    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
    好äºĭ
    -0.11
    æĻ¯å¾·
    -0.11
    èļį
    -0.10
    ä¿¡æģ¯åıijå¸ĥ
    -0.09
    ç³Ł
    -0.09
    oxide
    -0.09
    ä¸İæĹ¶ä¿±
    -0.09
    æ¦Ħ
    -0.09
    ä¸įåħį
    -0.09
    äºīåıĸ
    -0.09
    POSITIVE LOGITS
    éģĹ
    0.10
    çĭ¬æľīçļĦ
    0.09
    åı¹
    0.09
    ä¸ĸçķĮ级
    0.09
    çĭ¬çī¹çļĦ
    0.08
    hn
    0.08
    çĭ¬
    0.08
     met
    0.08
    orman
    0.08
    ä¾ĿçĦ¶
    0.08
    Activations Density 0.085%

    No Known Activations