© 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. 31765
    Prev
    Next
    INDEX
    Explanations

    Wat followed by specific endings

    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
    ors
    -0.10
    ãģĩ
    -0.10
    ality
    -0.10
    ipher
    -0.10
    bie
    -0.09
    eds
    -0.09
    avit
    -0.09
    halb
    -0.09
    Ùĩ
    -0.09
     annum
    -0.08
    POSITIVE LOGITS
    rd
    0.12
    æł·çļĦ
    0.11
    çīĩåŃIJ
    0.09
    ìĨIJ
    0.09
    ì§ľ
    0.09
    anders
    0.09
    å¢ŀå¹ħ
    0.09
    æ©Ľ
    0.08
    ransition
    0.08
    dır
    0.08
    Activations Density 0.032%

    No Known Activations