© 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. 53547
    Prev
    Next
    INDEX
    Explanations

    forgiven for, understandable if, natural

    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
    æĬ¹
    -0.10
    æĬĽå¼ĥ
    -0.10
    éĩįè¦ģåĨħ容
    -0.09
    仿
    -0.09
    çħ§å°Ħ
    -0.09
    æijĴ
    -0.08
    æµ·æ£ł
    -0.08
    è¿ĻæĿ¡è·¯
    -0.08
    çŃĶåºĶ
    -0.08
    注å®ļ
    -0.08
    POSITIVE LOGITS
    ãģĮãĤī
    0.10
    åĵī
    0.09
    æģ»
    0.09
    åħ³åĪĩ
    0.09
    ely
    0.09
    innen
    0.09
    zers
    0.09
    nel
    0.09
    äººåľ¨
    0.08
    æ±ĩ
    0.08
    Activations Density 0.010%

    No Known Activations