© 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. 35355
    Prev
    Next
    INDEX
    Explanations

    foreground or forefront

    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
     loc
    -0.11
    åIJijä¸ĭ
    -0.10
     hitch
    -0.09
    ä¸ķ
    -0.09
    igner
    -0.08
    éĶĢ
    -0.08
     dep
    -0.08
     leaf
    -0.08
    è¿ĺ好
    -0.08
    leaf
    -0.08
    POSITIVE LOGITS
     forefront
    0.15
     foreground
    0.14
    foreground
    0.14
    åīįåĪĹ
    0.14
    åīįåı°
    0.13
    çªģåĩº
    0.12
    Foreground
    0.12
    ToFront
    0.11
    çĦ¦çĤ¹
    0.11
     prominence
    0.11
    Activations Density 0.067%

    No Known Activations