© 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. 49553
    Prev
    Next
    INDEX
    Explanations

    virtual assistants and names

    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
    åĴĮåıijå±ķ
    -0.09
    馥
    -0.09
    led
    -0.09
    èī®
    -0.09
    aging
    -0.09
    æµģæĺŁ
    -0.09
    çļĩå¸Ŀ
    -0.08
    èľ©
    -0.08
    дал
    -0.08
    çļĭ
    -0.08
    POSITIVE LOGITS
    ipp
    0.10
     Justi
    0.09
    odem
    0.08
    ibase
    0.08
    ÑĢÑıд
    0.08
     fint
    0.08
    ince
    0.08
    Ĵ
    0.08
    è¦ģæĬĬ
    0.08
    ovable
    0.08
    Activations Density 0.009%

    No Known Activations