© 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. 38955
    Prev
    Next
    INDEX
    Explanations

    hand over / turn in

    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
    æıĦ
    -0.09
    åħ¶ä»ĸ人
    -0.08
    ennon
    -0.08
    åłij
    -0.08
    itecture
    -0.08
    åĢ¾
    -0.08
    ONENT
    -0.08
    çªŁ
    -0.08
    æľīåIJį
    -0.08
    éĥ½æĥ³
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģæī¹
    0.10
    äºĨä¸Ģ份
    0.09
    æł¼å°Ķ
    0.09
    ä¸Ģç¯ĩ
    0.09
    çľł
    0.09
    è¾ĺ
    0.08
    isson
    0.08
    äºĨä¸Ģ
    0.08
    彧
    0.08
    ил
    0.08
    Activations Density 0.007%

    No Known Activations