© 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. 18745
    Prev
    Next
    INDEX
    Explanations

    pick up

    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
    åĤ¥
    -0.10
    2
    -0.09
    å¯Ĵ
    -0.09
    1
    -0.09
     arrow
    -0.08
    3
    -0.08
    èŁij
    -0.08
    hom
    -0.08
    Green
    -0.08
     Arrow
    -0.08
    POSITIVE LOGITS
    æį¡
    0.15
    æĭ¾
    0.15
    æĭ£
    0.13
    .pick
    0.11
     pickups
    0.11
    æĭ¿èµ·
    0.11
     Pickup
    0.11
     pickup
    0.11
    æı½
    0.11
     picks
    0.10
    Activations Density 0.198%

    No Known Activations