© 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. 1340
    Prev
    Next
    INDEX
    Explanations

    U.S. News and publications

    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
     Ñģобой
    -0.10
    æķijåij½
    -0.10
    æ·±åħ¥äººå¿ĥ
    -0.09
     vale
    -0.09
    çľģåĨħ
    -0.09
    jax
    -0.09
    ector
    -0.09
    å«Ĥ
    -0.09
    çĬ¬
    -0.08
    ziej
    -0.08
    POSITIVE LOGITS
    çŀ©
    0.10
    iton
    0.08
    æĥ³åĪ°
    0.08
     Coalition
    0.08
    èı°
    0.08
    -gay
    0.08
     hẹn
    0.08
    ÑĨин
    0.08
     Parkway
    0.08
    å¡į
    0.08
    Activations Density 0.177%

    No Known Activations