© 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. 7580
    Prev
    Next
    INDEX
    Explanations

    intra- and inter-

    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
    _fds
    -0.09
    ÑĪка
    -0.09
    çľ¼éĩĮ
    -0.09
    adle
    -0.09
     Тем
    -0.09
    çļĦåľ°æĸ¹
    -0.09
    为ä¼ģä¸ļ
    -0.08
     hybrids
    -0.08
    .Focused
    -0.08
    绿水
    -0.08
    POSITIVE LOGITS
    ãģ¾ãģĹãģ¦
    0.10
    è¿ĻçĤ¹
    0.09
     circum
    0.09
    åIJĪä½ľåħ³ç³»
    0.09
    ãģĿãģĨãģ§
    0.09
    山路
    0.09
    ntl
    0.09
    lip
    0.08
    èĢĮè¿Ļ
    0.08
    ãģĽãģ¦
    0.08
    Activations Density 0.066%

    No Known Activations