© 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. 62673
    Prev
    Next
    INDEX
    Explanations

    hardware and software

    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
    æłī
    -0.10
    æĺº
    -0.09
     disruptive
    -0.08
    æĹ¶ä»£
    -0.08
    æĺ¼å¤ľ
    -0.08
    rete
    -0.08
    åĽłåħ¶
    -0.08
    бо
    -0.08
    å®ļä½į
    -0.08
     Forge
    -0.08
    POSITIVE LOGITS
    硬件
    0.23
     hardware
    0.19
     Hardware
    0.16
    hardware
    0.16
    Hardware
    0.15
    软件
    0.14
    .hardware
    0.14
     software
    0.13
    software
    0.12
    /software
    0.11
    Activations Density 0.159%

    No Known Activations