© 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. 61336
    Prev
    Next
    INDEX
    Explanations

    directed towards or against

    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
    è¿ĽåĨĽ
    -0.10
    å®ī康
    -0.10
    ä¸įåĪ©
    -0.10
    æīįèĥ½
    -0.09
    ç»
    -0.09
    èµĶ
    -0.09
    åħ¼
    -0.08
    å¼Ģä¼ļ
    -0.08
    çģŀ
    -0.08
    à¹ģà¸ŀ
    -0.08
    POSITIVE LOGITS
    ä¸Ģ份
    0.08
     Pope
    0.08
    ä¸įæŃ»
    0.08
    æݺ
    0.08
    ned
    0.08
    ä¸Ģå¤Ħ
    0.08
    inder
    0.08
    oro
    0.08
    INDER
    0.07
    æĶĴ
    0.07
    Activations Density 0.032%

    No Known Activations