© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36043
    Prev
    Next
    INDEX
    Explanations

    metaphorical objects or concepts

    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
     “
    -0.10
    itere
    -0.09
    aksi
    -0.09
    å±ĤéĿ¢
    -0.08
    ãĤ½ãĥ³
    -0.08
     rede
    -0.08
    nob
    -0.08
    å¢ĥçķĮ
    -0.08
    apers
    -0.07
     Mü
    -0.07
    POSITIVE LOGITS
    åŃ°
    0.10
    åĪĿ
    0.10
     пеÑĢев
    0.10
    æİīäºĨ
    0.09
    éĹ©
    0.09
    éģĹ
    0.09
    éģº
    0.09
    ĮĢ
    0.09
     Alam
    0.08
    åŀ«
    0.08
    Activations Density 0.082%

    No Known Activations