© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37628
    Prev
    Next
    INDEX
    Explanations

    explain things, tell stories

    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
    ested
    -0.10
    ãĢģãĢĮ
    -0.09
    isu
    -0.09
    ISING
    -0.09
    asaki
    -0.08
     Dun
    -0.08
    enes
    -0.08
    _NAMESPACE
    -0.08
    ardo
    -0.08
    åŀĤ
    -0.08
    POSITIVE LOGITS
    oe
    0.09
    æݸ
    0.09
    åĬłå¿«
    0.08
    åħ®
    0.08
    ç£Ķ
    0.08
    èݪ
    0.08
    妨
    0.08
    äºĶå¹´
    0.08
    oms
    0.08
    aus
    0.08
    Activations Density 0.153%

    No Known Activations