© 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. 19338
    Prev
    Next
    INDEX
    Explanations

    facing or oriented towards

    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
    zat
    -0.05
    udi
    -0.05
    åıijå¸ĥåħ¬åijĬ称
    -0.05
     complementary
    -0.05
    imana
    -0.05
     equally
    -0.05
    bil
    -0.05
    ä¸Ģæīĭ
    -0.05
    æīĭæľºä¸Ĭ
    -0.05
    amana
    -0.05
    POSITIVE LOGITS
    æľĿåIJij
    0.07
    æĬĽ
    0.07
    æľĿ
    0.06
    港澳åı°
    0.06
    inheit
    0.06
    باش
    0.06
     oriented
    0.06
    emble
    0.06
    çĽİ
    0.06
    ensus
    0.06
    Activations Density 0.023%

    No Known Activations