© 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. 22265
    Prev
    Next
    INDEX
    Explanations

    suffix of technical terms

    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
    adel
    -0.10
    åĬłå¿«
    -0.09
    åıł
    -0.09
    èIJģ
    -0.09
     Thần
    -0.09
    çĢĽ
    -0.08
    ARA
    -0.08
    æĵĴ
    -0.08
     nod
    -0.08
    .icon
    -0.08
    POSITIVE LOGITS
    usty
    0.10
    æŨ
    0.10
    壮
    0.09
    踢
    0.09
    дж
    0.09
     Eck
    0.09
    åıŁ
    0.09
    èĢķèĢĺ
    0.08
    åIJŃ
    0.08
    bugs
    0.08
    Activations Density 0.070%

    No Known Activations