© 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. 17218
    Prev
    Next
    INDEX
    Explanations

    Ten Commandments or Rights

    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
    çĬ¶åĨµ
    -0.10
    ainen
    -0.10
    æ°¸éģł
    -0.09
    æĽĻ
    -0.09
    _STS
    -0.09
    çĭĢæ³ģ
    -0.09
    ä¸Ģæľ¬
    -0.08
    ä¸įç»ıæĦı
    -0.08
    .decorate
    -0.08
    _DESCRIPTOR
    -0.08
    POSITIVE LOGITS
    ç®±
    0.09
    bes
    0.09
    Ñĥв
    0.08
    è¾Ł
    0.08
    æľīä¿¡å¿ĥ
    0.08
    رÙĩ
    0.08
    ลำ
    0.08
    æĥ³ä¸įåĪ°
    0.08
    è¿Ļ份
    0.08
    人å±ħ
    0.08
    Activations Density 0.090%

    No Known Activations