© 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. 28032
    Prev
    Next
    INDEX
    Explanations

    considering or contemplating future actions

    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
    éĹ»
    -0.09
    çĶ«
    -0.09
    å¥ł
    -0.09
    mutable
    -0.08
    äº
    -0.08
    ane
    -0.08
    agara
    -0.08
    çĦ°
    -0.08
    UIApplication
    -0.08
     kin
    -0.08
    POSITIVE LOGITS
     возможноÑģÑĤÑĮ
    0.11
     possibility
    0.11
    壮
    0.11
    念头
    0.11
    è´Ńç½®
    0.10
    æIJ¬å®¶
    0.10
    绸
    0.10
    ç½ijåıĭè¯Ħ论
    0.10
    è¦ģä¸įè¦ģ
    0.10
    è´Ńä¹°
    0.10
    Activations Density 0.142%

    No Known Activations