© 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. 21798
    Prev
    Next
    INDEX
    Explanations

    manufacturer's website or protocol

    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
    åķĨæľº
    -0.09
    åĵģè´¨
    -0.09
    磨æįŁ
    -0.09
    åħħ足
    -0.09
     PROVIDED
    -0.08
    AUTO
    -0.08
     buc
    -0.08
    heading
    -0.08
    cales
    -0.08
    opia
    -0.08
    POSITIVE LOGITS
    sic
    0.10
    éĤ£è¾¹
    0.09
    pliers
    0.09
    ï¸ı
    0.09
    è§Ħå®ļçļĦ
    0.08
    ally
    0.08
    滨
    0.08
    ipple
    0.08
     mf
    0.08
    å°±æĬĬ
    0.08
    Activations Density 0.015%

    No Known Activations