© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20321
    Prev
    Next
    INDEX
    Explanations

    polarization and orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    éŨåħ³
    -0.06
    uret
    -0.06
    lder
    -0.06
    ue
    -0.06
    #from
    -0.06
    æŃ¢è·Į
    -0.06
    uffed
    -0.06
    à¹Ģà¸Ĭืà¹Īà¸Ńม
    -0.06
    æ¼Ķ
    -0.06
    óf
    -0.06
    POSITIVE LOGITS
     directional
    0.08
     directions
    0.08
     orientations
    0.08
     orientation
    0.07
    direction
    0.07
     Orientation
    0.06
    æĸ¹åIJij
    0.06
    æŀķ
    0.06
     Directions
    0.06
    æĸ¹åIJijçļĦ
    0.06
    Activations Density 0.098%

    No Known Activations