© 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. 55550
    Prev
    Next
    INDEX
    Explanations

    bank efficiency and evaluation

    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
    宿
    -0.10
    èıŁ
    -0.08
    åľ°çĭ±
    -0.08
    agrant
    -0.08
    å¦ĵ
    -0.08
    åĵģä½į
    -0.08
    кÑĥÑĢ
    -0.08
    à¹Ĥà¸ģ
    -0.07
    容
    -0.07
     budget
    -0.07
    POSITIVE LOGITS
    è¡Įéķ¿
    0.16
    åĪĨè¡Į
    0.16
    åķĨä¸ļéĵ¶è¡Į
    0.15
    æĶ¯è¡Į
    0.15
    ç½ijçĤ¹
    0.15
    åŃĺ款
    0.14
    éĩijèŀįæľįåĬ¡
    0.14
    èµĦ管
    0.14
    .bank
    0.14
    è¾ĸ
    0.14
    Activations Density 0.211%

    No Known Activations