© 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. 50479
    Prev
    Next
    INDEX
    Explanations

    guess what happens

    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
    åĿĿ
    -0.10
    æĢİä¹Īçľĭ
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
    åľ¨è¿ĩ渡
    -0.09
    inia
    -0.09
    æ¢ħèĬ±
    -0.08
    -0.08
    åľĪåŃIJ
    -0.08
     arresting
    -0.08
    æį¢åıĸ
    -0.08
    POSITIVE LOGITS
    æĻĸ
    0.10
    unist
    0.09
    åĢĴéľī
    0.08
    наÑĤ
    0.08
    禽
    0.08
    åĩºå¸Ń
    0.08
    æĻĶ
    0.08
    éļ³
    0.08
    ERICA
    0.08
    rey
    0.08
    Activations Density 0.004%

    No Known Activations