© 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. 61614
    Prev
    Next
    INDEX
    Explanations

    Rap, rap, ap related sequences

    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
    ãģĹãģ¾ãģĦ
    -0.10
    çĿĽ
    -0.09
    liness
    -0.09
    å¿¡
    -0.09
    ãĤº
    -0.09
    çıĢ
    -0.09
    æĢĢçĿĢ
    -0.09
    asers
    -0.09
    nement
    -0.08
    æĢħ
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.11
    sters
    0.10
    apel
    0.09
    次æķ°
    0.09
    ðŁı»
    0.09
    pped
    0.09
    ulator
    0.09
    riot
    0.09
     обоÑĢ
    0.08
    åıįæŃ£
    0.08
    Activations Density 0.009%

    No Known Activations