© 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. 48042
    Prev
    Next
    INDEX
    Explanations

    sticking to it

    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
    èħ¾é£ŀ
    -0.10
    ä¿Ŀå®Ī
    -0.10
    笺
    -0.09
    ÅĤaw
    -0.09
    åĤį
    -0.08
    éĺħåİĨ
    -0.08
    xit
    -0.08
    revision
    -0.08
     sen
    -0.08
    apas
    -0.08
    POSITIVE LOGITS
    åIJijçĿĢ
    0.12
    缴åĪ°
    0.11
     persistence
    0.10
    åĽłä¸ºæĪij
    0.10
    ä¸įæĩĪ
    0.10
    飧
    0.10
    缴èĩ³
    0.10
    æ¯ħ
    0.10
    åĽłä¸ºå®ĥ
    0.09
    åıªæľīä¸Ģ个
    0.09
    Activations Density 0.185%

    No Known Activations