© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21247
    Prev
    Next
    INDEX
    Explanations

    of [place/group]

    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
     назад
    -0.09
    å¬ĸ
    -0.08
    æ·Į
    -0.08
    çħ¦
    -0.08
    3
    -0.08
    çľŃ
    -0.08
    7
    -0.08
    4
    -0.08
    ÙĦاÙģ
    -0.08
     sized
    -0.08
    POSITIVE LOGITS
    Ñıм
    0.10
    æĿĵ
    0.10
     Gon
    0.09
    onas
    0.09
    quired
    0.09
    ä½ķå¤Ħ
    0.08
    çĦī
    0.08
    åĨľå®¶
    0.08
    å®ļäºĨ
    0.08
    åĸĦèī¯
    0.08
    Activations Density 0.044%

    No Known Activations