© 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. 2325
    Prev
    Next
    INDEX
    Explanations

    friends and finding

    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
     Bey
    -0.09
    æģIJ
    -0.09
     Bun
    -0.09
    æīĢæıIJä¾Ľ
    -0.08
    审
    -0.08
    éĿ©
    -0.08
    nova
    -0.08
     anim
    -0.08
    绿
    -0.08
    åĩłåĪĨéĴŁ
    -0.08
    POSITIVE LOGITS
    紧迫
    0.10
    _scalar
    0.09
    é«Ń
    0.09
    erce
    0.09
    blr
    0.09
    ountain
    0.09
    å¼ıçļĦ
    0.09
    æ²īéĩį
    0.09
    calar
    0.09
    强çĥĪçļĦ
    0.09
    Activations Density 0.001%

    No Known Activations