© 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. 31022
    Prev
    Next
    INDEX
    Explanations

    fledgling, blown, archetypal

    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
    ÄĻk
    -0.09
    带
    -0.09
     Gel
    -0.09
    磼
    -0.09
    asel
    -0.08
    ÅŁtir
    -0.08
    çĤ¹å¤ļ
    -0.08
    bez
    -0.08
    itud
    -0.08
    ajan
    -0.08
    POSITIVE LOGITS
    otypical
    0.10
    åįģ足
    0.09
    çĭĦ
    0.09
     forg
    0.09
    eme
    0.08
    å´¤
    0.08
    ement
    0.08
    åħįè´£
    0.08
    ep
    0.08
    ãĥ¤
    0.08
    Activations Density 0.001%

    No Known Activations