© 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. 21865
    Prev
    Next
    INDEX
    Explanations

    one another

    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
    steen
    -0.10
    lein
    -0.09
    iveness
    -0.09
    åģķ
    -0.09
    浪
    -0.09
    virt
    -0.09
    è·»
    -0.09
    ãĢĿ
    -0.09
    çĵ®
    -0.09
    èĬŃ
    -0.08
    POSITIVE LOGITS
    aday
    0.08
     babys
    0.07
    opt
    0.07
    ter
    0.07
    bell
    0.07
     Saud
    0.07
     vera
    0.07
     Adler
    0.07
     Moff
    0.07
     Quarter
    0.07
    Activations Density 0.007%

    No Known Activations