© 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. 21998
    Prev
    Next
    INDEX
    Explanations

    providing service, information, or functions

    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
    vas
    -0.09
    å®ķ
    -0.09
    agli
    -0.08
     Confeder
    -0.08
    deer
    -0.08
    äºĭåIJİ
    -0.08
    íĮIJ
    -0.08
    åĴİ
    -0.08
    èĬĥ
    -0.08
    _pod
    -0.08
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.10
     Balk
    0.10
    ç»Ļä»ĸ们
    0.09
     возможноÑģÑĤÑĮ
    0.09
    åı¯èĥ½æĢ§
    0.09
    åħħè£ķ
    0.08
    æ·±åĪ»çļĦ
    0.08
    客æĪ·æıIJä¾Ľ
    0.08
    éĥ
    0.08
    å°¼åħĭ
    0.08
    Activations Density 0.105%

    No Known Activations