© 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. 48469
    Prev
    Next
    INDEX
    Explanations

    places and locations

    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
    è¡ĮåĬ¨
    -0.10
    åħ¨çº¿
    -0.09
    ä¸ĢçŃīå¥ĸ
    -0.09
    æ»Ĥ
    -0.09
    ä»ĸåľ¨
    -0.09
    ä¸ĢæĹı
    -0.08
    主åĬĽåĨĽ
    -0.08
    åıijæī¬
    -0.08
    bundles
    -0.08
    eday
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåľ°æĸ¹
    0.16
     places
    0.15
    åľºæīĢ
    0.14
    åħ¬åħ±åľºæīĢ
    0.14
    places
    0.13
    ä½ķå¤Ħ
    0.13
    åĵªéĩĮ
    0.13
    æĪĺåľº
    0.13
    (place
    0.12
     меÑģÑĤа
    0.12
    Activations Density 0.153%

    No Known Activations