© 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. 30965
    Prev
    Next
    INDEX
    Explanations

    economic crisis

    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
    ture
    -0.10
    /IP
    -0.10
    ings
    -0.10
    ife
    -0.09
    lying
    -0.09
    ities
    -0.09
     Vog
    -0.09
    åĩĮæĻ¨
    -0.09
    彬
    -0.09
    wise
    -0.09
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    çĺķ
    0.10
    -era
    0.09
    äºĮèĢħ
    0.09
    严éĩįçļĦ
    0.09
    人éĢł
    0.09
    åĴĮåıijå±ķ
    0.08
    вали
    0.08
    管å§Ķä¼ļ
    0.08
    _OCCURRED
    0.08
    Activations Density 0.005%

    No Known Activations