© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21681
    Prev
    Next
    INDEX
    Explanations

    dimensional travel, portals, teleport, time warp

    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
    ç»Ī身
    -0.10
    èĥĦ
    -0.09
    rov
    -0.09
    arov
    -0.09
    æĭį
    -0.09
    eties
    -0.09
    é¦Ĩ
    -0.09
    åįĩåĢ¼
    -0.09
    çĬ¯
    -0.08
    /^
    -0.08
    POSITIVE LOGITS
    ç©¿è¶Ĭ
    0.16
    ç©¿æ¢Ń
    0.13
    è·³è·ĥ
    0.12
     teleport
    0.11
    .portal
    0.11
    ä¼łéĢģ
    0.11
     portals
    0.11
    éĢļå¾Ģ
    0.10
    æŀ¢çº½
    0.10
    éŨæĪ·
    0.10
    Activations Density 0.069%

    No Known Activations