© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8443
    Prev
    Next
    INDEX
    Explanations

    public sector

    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
    ãģĹãģ¾ãģĨ
    -0.11
    thed
    -0.10
    ense
    -0.09
    -hearted
    -0.09
    ãģĹãģ¾
    -0.09
    çĽĴ
    -0.08
    ness
    -0.08
    OrCreate
    -0.08
    å±±èĦī
    -0.08
    ãģĹãģĦ
    -0.08
    POSITIVE LOGITS
    ally
    0.13
    åĨħçļĦ
    0.12
    åĬĽéĩı
    0.11
    ftware
    0.11
    -leading
    0.10
    人士
    0.10
    ible
    0.10
    iva
    0.10
    ively
    0.10
    åĮĸçļĦ
    0.10
    Activations Density 0.008%

    No Known Activations