© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21862
    Prev
    Next
    INDEX
    Explanations

    inner self or soul

    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
    æĭĶ
    -0.08
    å¹»æĥ³
    -0.08
    .ci
    -0.08
    亨
    -0.08
    8
    -0.07
    7
    -0.07
     slightly
    -0.07
    «
    -0.07
    imuth
    -0.07
    1
    -0.07
    POSITIVE LOGITS
    åĨħåľ¨
    0.15
    å¤ĸ表
    0.14
     zewnÄĻtrzn
    0.12
    åĨħ饰
    0.11
    /Internal
    0.11
    æķ£åıij
    0.11
    åĨħ涵
    0.11
    (internal
    0.11
     внÑĥÑĤ
    0.10
    容è²Į
    0.10
    Activations Density 0.034%

    No Known Activations