© 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. 62186
    Prev
    Next
    INDEX
    Explanations

    solo artist and freelance work

    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
    sWith
    -0.11
    ened
    -0.09
    ments
    -0.09
    ijke
    -0.08
    standing
    -0.08
    ãģ®ãģĮ
    -0.08
    uir
    -0.08
    iable
    -0.08
    åīįçŀ»
    -0.08
    duino
    -0.08
    POSITIVE LOGITS
    èĪ«
    0.10
    ðŁı»
    0.10
    åĽłä¸ºå¥¹
    0.10
    CEED
    0.10
    çįŃ
    0.09
    窿
    0.09
    ðŁı½
    0.09
    ansi
    0.09
    IALIZ
    0.09
    agens
    0.09
    Activations Density 0.022%

    No Known Activations