© 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. 19850
    Prev
    Next
    INDEX
    Explanations

    seeking attention or spotlight

    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
    kk
    -0.06
    æĪijä¹Łåİ»
    -0.06
    bio
    -0.06
     lookout
    -0.06
    биÑĤ
    -0.05
    Tap
    -0.05
    iveness
    -0.05
    hq
    -0.05
    æĽ´å¹¿
    -0.05
    vel
    -0.05
    POSITIVE LOGITS
    emani
    0.06
    媲ç¾İ
    0.06
    çĭ¬åįł
    0.05
    ãĥķãĤ¡ãĥ¼
    0.05
    æħ°
    0.05
     chamber
    0.05
    er
    0.05
    ä½İèĩ³
    0.05
    ä¸Ńå¿ĥåĮĸ
    0.05
    acher
    0.05
    Activations Density 0.002%

    No Known Activations