© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38548
    Prev
    Next
    INDEX
    Explanations

    oil price and gasoline

    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
    èľĤèľľ
    -0.08
    è¹²
    -0.08
    使åij½
    -0.08
    太快
    -0.08
     Carpet
    -0.08
     hired
    -0.08
    çģ¿çĥĤ
    -0.08
    女
    -0.08
    åıĪæľī
    -0.08
    ç³ĸæŀľ
    -0.08
    POSITIVE LOGITS
    æ²¹æ°Ķ
    0.13
    åİŁæ²¹
    0.12
    油价
    0.11
    çŁ³æ²¹
    0.10
    åĬłæ²¹ç«Ļ
    0.10
    çŁ³æ²¹åĮĸå·¥
    0.10
    çĩĥæ²¹
    0.10
    çĩĥæĸĻ
    0.10
    æ²¹
    0.10
     gallon
    0.10
    Activations Density 0.143%

    No Known Activations