© 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. 3897
    Prev
    Next
    INDEX
    Explanations

    acts, casts, logs

    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
    sWith
    -0.18
    swith
    -0.17
    (s
    -0.15
    sto
    -0.15
    spath
    -0.13
    's
    -0.13
    ss
    -0.13
     اÙĦÙĪاØŃد
    -0.13
    åŃIJéĩĮ
    -0.12
    stype
    -0.12
    POSITIVE LOGITS
    ervice
    0.19
    cape
    0.18
    uite
    0.17
    ystem
    0.17
    pace
    0.17
    heet
    0.16
    cales
    0.16
    mith
    0.16
    ource
    0.15
    cheme
    0.15
    Activations Density 5.001%

    No Known Activations