© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22050
    Prev
    Next
    INDEX
    Explanations

    strengths

    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
    mith
    -0.06
    ож
    -0.06
    ulate
    -0.05
    ä¸ĢåĪĻ
    -0.05
    _enc
    -0.05
    zum
    -0.05
    ãģ®ãĤĴ
    -0.05
     fak
    -0.05
     Altern
    -0.05
    hare
    -0.05
    POSITIVE LOGITS
    å½¢
    0.06
    entra
    0.06
     Fokus
    0.06
    ä¿¡æģ¯çĶ±
    0.06
    åĮħ容
    0.06
    主次
    0.06
    Ñĥго
    0.06
    ivement
    0.05
    OfWork
    0.05
     focal
    0.05
    Activations Density 0.002%

    No Known Activations