© 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. 37063
    Prev
    Next
    INDEX
    Explanations

    golden gate

    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
    èĪ£
    -0.10
    inded
    -0.09
    迹象
    -0.09
    _MAXIMUM
    -0.09
    ifar
    -0.08
    _ROW
    -0.08
    åħħ
    -0.08
    梢
    -0.08
    burger
    -0.08
    é¹ĺ
    -0.08
    POSITIVE LOGITS
     golden
    0.13
     Golden
    0.12
    golden
    0.12
    çĥģ
    0.12
    éĩijèī²
    0.12
    éĩij
    0.11
    é»Ħéĩij
    0.11
    çĻ½éĵ¶
    0.10
    Golden
    0.10
    è´µ
    0.10
    Activations Density 0.066%

    No Known Activations