© 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. 32934
    Prev
    Next
    INDEX
    Explanations

    purpose and its function

    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
    çĪ±ä¸Ĭ
    -0.09
    ä»İä¸Ń
    -0.09
    ogh
    -0.08
    rone
    -0.08
    .Bounds
    -0.08
    å¼Ħ
    -0.08
    utches
    -0.08
    æĦŁåħ´è¶£çļĦ
    -0.08
    转移åĪ°
    -0.08
    æİĺ
    -0.08
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.25
     purpose
    0.20
     purposes
    0.19
    purpose
    0.18
    Purpose
    0.17
    ä½ľçĶ¨
    0.17
    缮çļĦ
    0.16
     Purpose
    0.16
    çļĦä½ľçĶ¨
    0.16
    -purpose
    0.15
    Activations Density 0.252%

    No Known Activations