© 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. 55988
    Prev
    Next
    INDEX
    Explanations

    access and unlock

    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
    å¼ĥ
    -0.09
    ä¿¡èµĸ
    -0.09
    寻
    -0.09
    çļĦéĴ±
    -0.09
     Ebay
    -0.09
    æīĢå¾Ĺ
    -0.08
    è¡Įæĥħ
    -0.08
    ì¤Ħ
    -0.08
    å¤ĩçĶ¨
    -0.08
    CDATA
    -0.08
    POSITIVE LOGITS
    é½IJåħ¨
    0.12
     unlocked
    0.11
    å®Įæķ´çļĦ
    0.11
    解éĶģ
    0.10
    å®Įæķ´
    0.10
     access
    0.10
    ä»ĺè´¹
    0.09
    Access
    0.09
    _access
    0.09
    ACCESS
    0.09
    Activations Density 0.049%

    No Known Activations