© 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. 48673
    Prev
    Next
    INDEX
    Explanations

    send you / a / an / additional / out

    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
    åĿ¨
    -0.11
    鼶è·Ŀ离
    -0.11
    åģļ个
    -0.10
    yna
    -0.10
    å±ħ室
    -0.10
    å¥ı
    -0.10
     hạng
    -0.09
    кам
    -0.09
    åľŃ
    -0.09
    StackSize
    -0.09
    POSITIVE LOGITS
     Ñĥни
    0.09
    _UID
    0.08
    inel
    0.08
    è¶³å¤Ł
    0.08
    æķijçģ¾
    0.08
    imps
    0.08
    æ··æ·Ĩ
    0.08
    inality
    0.08
     abroad
    0.08
    agenta
    0.08
    Activations Density 0.015%

    No Known Activations