© 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. 49435
    Prev
    Next
    INDEX
    Explanations

    restore

    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
    ersion
    -0.10
    isia
    -0.10
    ä»įå°Ĩ
    -0.09
     impro
    -0.09
    atility
    -0.09
    ersistence
    -0.09
    ossal
    -0.08
    éķ¿çĽ¸
    -0.08
    pheres
    -0.08
    åĩŃè¯ģ
    -0.08
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.16
     lost
    0.15
    Lost
    0.13
    lost
    0.13
    åİŁæľī
    0.13
    é¢ĵ
    0.12
    丢失
    0.12
    失èIJ½
    0.11
    æĺĶæĹ¥
    0.11
    åİŁæľ¬
    0.11
    Activations Density 0.088%

    No Known Activations