© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21318
    Prev
    Next
    INDEX
    Explanations

    causal phrasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inder
    -0.07
    ianos
    -0.06
    inter
    -0.06
    ÙħاÙĥ
    -0.06
    ursa
    -0.06
    ixer
    -0.06
    亿åħĥ人æ°ijå¸ģ
    -0.06
    its
    -0.06
    å§
    -0.05
    true
    -0.05
    POSITIVE LOGITS
     oneself
    0.09
    icare
    0.09
     particuliers
    0.08
     lanjut
    0.08
    anford
    0.08
     origini
    0.08
    icator
    0.08
    ÑĤÑģÑı
    0.07
    åİŁåĪĽä½ľåĵģ
    0.07
    å¥½ä¸ľè¥¿
    0.07
    Activations Density 0.535%

    No Known Activations