© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7342
    Prev
    Next
    INDEX
    Explanations

    ingredients and amounts

    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
    伸åĩº
    -0.09
    æķ·
    -0.09
    oad
    -0.08
    åIJ¸
    -0.08
     Chew
    -0.08
    GetX
    -0.08
    .sam
    -0.08
    姿åĬ¿
    -0.08
    .transitions
    -0.08
    ultipart
    -0.08
    POSITIVE LOGITS
    åĬłåħ¥
    0.13
    çĶ¨éĩı
    0.11
     ingredients
    0.11
    åĬłåħ¥äºĨ
    0.11
    éĢĤéĩı
    0.10
    çļĦæ¯Ķä¾ĭ
    0.10
    æݧ
    0.10
    åħij
    0.10
     amount
    0.10
    大éĩıçļĦ
    0.10
    Activations Density 0.040%

    No Known Activations