© 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. 51305
    Prev
    Next
    INDEX
    Explanations

    unemployed or job loss

    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
    ä¸Ģæīĭ
    -0.10
     ima
    -0.09
    icast
    -0.09
    /IP
    -0.09
    åıijèĤ²
    -0.09
    uala
    -0.09
    .Alpha
    -0.09
    åµĺ
    -0.09
    enstein
    -0.09
    级
    -0.09
    POSITIVE LOGITS
    太ä¹ħ
    0.09
    诰
    0.08
    osphere
    0.08
    ä¹Ķ
    0.08
    ä¹ħäºĨ
    0.08
    éĥ¨å§Ķ
    0.08
    åģļå®Į
    0.08
    atable
    0.08
     Cmd
    0.08
    åĽłä¸ºä»ĸ
    0.08
    Activations Density 0.014%

    No Known Activations