© 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. 50091
    Prev
    Next
    INDEX
    Explanations

    lift, elevate, or soar

    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
    å®ļçĤ¹
    -0.09
    rou
    -0.08
    prov
    -0.08
    ado
    -0.08
    æħ
    -0.08
    çĢļ
    -0.08
    ç«ł
    -0.08
    rig
    -0.08
    ylon
    -0.08
    两çĤ¹
    -0.08
    POSITIVE LOGITS
    .lift
    0.10
    Ñħодим
    0.10
    è¹Ī
    0.10
     elev
    0.09
    ÑĤоÑĢ
    0.09
    lov
    0.09
    .Assertions
    0.09
    èĵĸ
    0.09
    ment
    0.09
    IBC
    0.09
    Activations Density 0.017%

    No Known Activations