© 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. 48289
    Prev
    Next
    INDEX
    Explanations

    home and its surroundings

    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
    ivent
    -0.10
    dom
    -0.09
    .bs
    -0.09
    adic
    -0.09
    åĩŃä»Ģä¹Ī
    -0.09
    累积
    -0.09
    ively
    -0.09
    éĩİçĶŁ
    -0.09
    çĹ¢
    -0.09
    icit
    -0.09
    POSITIVE LOGITS
    аÑĪ
    0.09
    BuilderInterface
    0.09
    ick
    0.08
    éĩĮçļĦ
    0.08
    owner
    0.08
    çļĦéĢīæĭ©
    0.08
    puter
    0.08
    ದ
    0.08
    _DAY
    0.08
    èĢģåŃIJ
    0.08
    Activations Density 0.031%

    No Known Activations