© 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. 4091
    Prev
    Next
    INDEX
    Explanations

    doing it wrong

    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
    ijn
    -0.09
    æīĵèµ·
    -0.08
    ä¸įçĶ¨è¯´
    -0.07
    ÑģаÑĢ
    -0.07
    åĨįä¹Łä¸į
    -0.07
    кнÑĥ
    -0.06
    ä»»ä½ķæŶåĢĻ
    -0.06
    åħ¨åĽ½çļĦ
    -0.06
    ä¸ľè¥¿
    -0.06
    amble
    -0.06
    POSITIVE LOGITS
    æľªåĪ°
    0.09
     haven
    0.08
    ä¸įå½ĵ
    0.08
     недоÑģÑĤаÑĤоÑĩно
    0.08
    ä¸įåĪ°
    0.08
    å®£ä¼łåĬĽåº¦
    0.08
    没æľīæī¾åĪ°
    0.08
     genuinely
    0.07
     wasn
    0.07
     hasn
    0.07
    Activations Density 0.244%

    No Known Activations