© 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. 50420
    Prev
    Next
    INDEX
    Explanations

    him and return alone

    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
    ackson
    -0.08
    éģ¸äºº
    -0.08
    erule
    -0.08
    anya
    -0.08
    æ¡ĪçĶ±
    -0.07
    oreach
    -0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    onz
    -0.07
    roid
    -0.07
    ahir
    -0.07
    POSITIVE LOGITS
    ãĤ¹ãĤ«
    0.06
    毫
    0.06
    اب
    0.06
    俱
    0.06
    λοÏħ
    0.06
    裾
    0.06
    å½ĵåºŃ
    0.06
    è®®
    0.06
    å¸Ĥè´¢æĶ¿å±Ģ
    0.06
     NOTIFY
    0.06
    Activations Density 0.011%

    No Known Activations