© 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. 18129
    Prev
    Next
    INDEX
    Explanations

    whatever

    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
    /or
    -0.10
    åħĦ
    -0.10
    åĨĮ
    -0.09
    åĪĿæŃ¥
    -0.08
    fulness
    -0.08
    ìį¨
    -0.08
    ACHE
    -0.08
    éļ¼
    -0.08
    åĨĬ
    -0.08
    ä¸Ģç¬ij
    -0.08
    POSITIVE LOGITS
    ETA
    0.10
    说æĺ¯
    0.10
    /e
    0.10
    ood
    0.09
    ités
    0.09
    çĸĥ
    0.09
    lef
    0.09
    èĥ½æī¾åĪ°
    0.09
    EntryPoint
    0.09
    entai
    0.09
    Activations Density 0.012%

    No Known Activations