© 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. 47869
    Prev
    Next
    INDEX
    Explanations

    way, goes, go, far

    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
    æ¯ıå¹´éĥ½
    -0.09
    大åºĨ
    -0.09
    èij£
    -0.09
     VÅ©
    -0.09
    åºĶåıĬæŶ
    -0.09
    æľĢåħĪè¿ĽçļĦ
    -0.09
    çĮĿ
    -0.09
    æĺİæĻº
    -0.08
    æ¯Ľ
    -0.08
     Collins
    -0.08
    POSITIVE LOGITS
    å°ij许
    0.09
    udo
    0.09
    ODO
    0.09
    UDO
    0.09
     Mile
    0.08
    ondo
    0.08
    pei
    0.08
    ioni
    0.08
    ilot
    0.08
    çħ§é¡¾
    0.08
    Activations Density 0.056%

    No Known Activations