© 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. 35457
    Prev
    Next
    INDEX
    Explanations

    news media and sports outlets

    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
    æĢİä¹Īçľĭ
    -0.10
    æĮģæľī人
    -0.09
    åħ«åį¦
    -0.09
    æ´»
    -0.09
    æľĭ
    -0.09
     ÐĵÑĢ
    -0.09
    åĪ©æ¶¦çİĩ
    -0.08
    ç²ķ
    -0.08
    缼
    -0.08
    åıĺåİĭ
    -0.08
    POSITIVE LOGITS
    å¹ķ
    0.10
    LabelText
    0.09
    achable
    0.09
    arshal
    0.08
    yll
    0.08
     transcripts
    0.08
     Pruitt
    0.08
    elper
    0.08
    NavItem
    0.08
     Huff
    0.08
    Activations Density 0.022%

    No Known Activations