© 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. 52646
    Prev
    Next
    INDEX
    Explanations

    hardship and adversity

    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
    çĽĨåľ°
    -0.09
    æŃĨ
    -0.09
    ä¸įæ¸ħæ¥ļ
    -0.09
    éĴī
    -0.09
    ett
    -0.08
    eted
    -0.08
    æĥ³åĪ°
    -0.08
    ULAR
    -0.08
    engo
    -0.08
     Oswald
    -0.08
    POSITIVE LOGITS
    ioned
    0.11
     ÑĤÑĥ
    0.09
     Gould
    0.08
    Ñıз
    0.08
    enna
    0.08
    agram
    0.08
    wend
    0.08
    çĻ¾å§ĵ
    0.08
    ança
    0.08
    ingham
    0.08
    Activations Density 0.013%

    No Known Activations