© 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. 8855
    Prev
    Next
    INDEX
    Explanations

    at or within

    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
    iles
    -0.10
    onium
    -0.10
    ÑĭÑĪ
    -0.09
     sol
    -0.08
    è¿Ń
    -0.08
    è¯Ĩ
    -0.08
    å¤ļä¹ħ
    -0.08
    ILES
    -0.08
     sinking
    -0.08
    çŁ¥ä¹İ
    -0.08
    POSITIVE LOGITS
    éľ²
    0.09
    å´Ń
    0.09
    ires
    0.09
    Ħ件
    0.08
    à¹Ģลย
    0.08
    auce
    0.08
    åĺīå¹´
    0.08
    åľ°æłĩ
    0.08
    df
    0.08
    ä¸Ģæīĭ
    0.08
    Activations Density 0.391%

    No Known Activations