© 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. 61921
    Prev
    Next
    INDEX
    Explanations

    ecosystem components and functions

    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
    æ°ijæĶ¿
    -0.09
    маÑĢ
    -0.08
     маÑĢ
    -0.08
    åħīæĺİ
    -0.08
     marca
    -0.08
    泡
    -0.08
    åĮĹ约
    -0.08
    Refreshing
    -0.08
    温
    -0.08
    mar
    -0.07
    POSITIVE LOGITS
    çĶŁæĢģç³»ç»Ł
    0.13
    çĶŁæĢģ
    0.12
    çĶŁæĢģåľĪ
    0.12
     ecosystem
    0.11
     interactions
    0.10
    -pencil
    0.10
     ecosystems
    0.10
    ecal
    0.10
    cosystem
    0.09
    ORN
    0.09
    Activations Density 0.070%

    No Known Activations