© 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. 23168
    Prev
    Next
    INDEX
    Explanations

    names ending in 'ier', 'etti', 'in', 'inski', 'ison'

    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
    ä¸ĢåĪĢ
    -0.12
    客åİħ
    -0.09
    çļĦè¯Ŀé¢ĺ
    -0.09
    ä¸Ģå¤Ħ
    -0.09
    ä¸ĢåıĮ
    -0.09
    座
    -0.09
    è¯Ŀé¢ĺ
    -0.09
     indirect
    -0.08
    åĵį
    -0.08
    gne
    -0.08
    POSITIVE LOGITS
    avar
    0.09
    æļĸ
    0.09
    SAFE
    0.08
     اÙĦعÙħر
    0.08
    BERS
    0.08
    æ³ī
    0.08
    èŀºæĹĭ
    0.08
    arks
    0.08
    AGIC
    0.08
    .spi
    0.08
    Activations Density 0.092%

    No Known Activations