© 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. 19013
    Prev
    Next
    INDEX
    Explanations

    scores after losing

    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
    맥
    -0.08
    åŁºæķ°
    -0.08
    代è¨Ģ
    -0.08
    æłĩè¯Ń
    -0.08
    ulle
    -0.08
    _far
    -0.08
    onium
    -0.08
    ×
    -0.08
    çĤĴä½ľ
    -0.08
    Syntax
    -0.08
    POSITIVE LOGITS
    éľĩ
    0.12
    漫
    0.10
    æį·
    0.09
    ä¸Ģåľº
    0.09
    ouro
    0.09
    éĺħ读åħ¨æĸĩ
    0.08
    aur
    0.08
    обоÑĢ
    0.08
    æľµ
    0.08
    éĿ¡
    0.08
    Activations Density 0.095%

    No Known Activations