© 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. 45805
    Prev
    Next
    INDEX
    Explanations

    contraction or expansion

    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
    è¾Ľè¾Ľèĭ¦
    -0.08
    å§ĭèĩ³
    -0.08
    çīĮåŃIJçļĦ
    -0.08
    ÐŁÐļ
    -0.08
    åħ¬åı¸åIJij
    -0.08
    ITHER
    -0.08
    ittest
    -0.07
    ToInt
    -0.07
    ä½ľä¸ºä¸Ģç§į
    -0.07
    ickl
    -0.07
    POSITIVE LOGITS
    为æŃ¢
    0.10
    åĨįåĪ°
    0.10
    çļĦè¿ĩç¨ĭä¸Ń
    0.09
    çĦ¶åIJİåĨį
    0.09
    çĦ¶åIJİåıĪ
    0.08
    çĤºæŃ¢
    0.08
    åĨįçĶ±
    0.08
     usable
    0.08
    ä¸Ńåİ»
    0.08
     via
    0.08
    Activations Density 0.385%

    No Known Activations