© 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. 35272
    Prev
    Next
    INDEX
    Explanations

    willing to sacrifice

    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
     fut
    -0.10
    åıįçľģ
    -0.09
    éŀŃ
    -0.08
    å²ĺ
    -0.08
    elta
    -0.08
     Vict
    -0.08
    åĬłæ²¹
    -0.08
    åIJ¸
    -0.08
    å«Įçĸij
    -0.08
    olem
    -0.08
    POSITIVE LOGITS
    ä¸įæĥľ
    0.17
    å®ģæĦ¿
    0.13
    çīºçī²
    0.12
    ä¸ĢåĪĩ
    0.11
    åĴĮå¹³
    0.11
    èªĵ
    0.10
     sacrific
    0.10
     Sacr
    0.10
     sacrifice
    0.10
    åĪ³
    0.10
    Activations Density 0.083%

    No Known Activations