© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51438
    Prev
    Next
    INDEX
    Explanations

    email related phrases

    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
    ively
    -0.12
    iful
    -0.10
    ate
    -0.09
    fare
    -0.09
    udd
    -0.09
    iveness
    -0.08
    eur
    -0.08
     Valk
    -0.08
    OfString
    -0.08
    _execution
    -0.08
    POSITIVE LOGITS
    械
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    afen
    0.10
    @example
    0.09
    ight
    0.09
    unga
    0.09
    çijķ
    0.09
    perator
    0.09
    anes
    0.09
    ä¸Ģå°ģ
    0.09
    Activations Density 0.023%

    No Known Activations