© 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. 33652
    Prev
    Next
    INDEX
    Explanations

    Lo Green,ipay,opath

    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
    íĮ©
    -0.09
    ment
    -0.09
    åĸĻ
    -0.09
     Belgi
    -0.09
    æĪİ
    -0.09
    éĻ¤æѤ
    -0.09
    ä¸Ĭå¹´
    -0.09
    æģ¶å¿ĥ
    -0.08
    ænd
    -0.08
    è¸Į
    -0.08
    POSITIVE LOGITS
    ä¸įè§ģ
    0.09
    俦
    0.09
    ooth
    0.09
    ego
    0.08
     Pitch
    0.08
    ion
    0.08
    骡
    0.08
    _angles
    0.08
    gos
    0.08
     curl
    0.08
    Activations Density 0.001%

    No Known Activations