© 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. 37857
    Prev
    Next
    INDEX
    Explanations

    foster family or care

    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
    OrDefault
    -0.10
    ãĥ¥
    -0.10
    ÑĥÑĢ
    -0.10
    ï¸
    -0.09
    uted
    -0.08
    thic
    -0.08
    Ñģлед
    -0.08
    举æĸ¹è´¢å¯Į
    -0.08
    sert
    -0.08
    å´Ĩ
    -0.08
    POSITIVE LOGITS
    ively
    0.11
    à¸ģาย
    0.10
    .za
    0.09
    æĪIJçĨŁçļĦ
    0.09
    ðŁı»
    0.09
    çīĩåĪ»
    0.09
    ments
    0.09
    aying
    0.09
    ayed
    0.09
    ement
    0.09
    Activations Density 0.008%

    No Known Activations