© 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. 33846
    Prev
    Next
    INDEX
    Explanations

    no or not

    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
    nl
    -0.09
    åŃļ
    -0.09
    alach
    -0.09
    ocs
    -0.08
    onest
    -0.08
    å¿«éĢŁåıijå±ķ
    -0.08
    æĸ°çļĦä¸Ģå¹´
    -0.08
    ä¸įæŃ¢
    -0.08
    è¿Ļä¸įæĺ¯
    -0.08
    åĬ¡å®ŀ
    -0.08
    POSITIVE LOGITS
    /vendor
    0.11
    æľīä»»ä½ķ
    0.11
     há»ģ
    0.11
    åħ¶ä»ĸ
    0.10
    ificio
    0.10
    çģ«çĥ§
    0.09
    åħ¼é¡¾
    0.09
    inium
    0.09
    .googleapis
    0.09
    ÑĢÑĥг
    0.09
    Activations Density 0.276%

    No Known Activations