© 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. 12573
    Prev
    Next
    INDEX
    Explanations

    Fe.fwdarw.Fe.sup.2+

    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
    izard
    -0.06
     اÙĦدراسÙĬ
    -0.06
    igraphy
    -0.06
    æĬķèµĦé£İéĻ©
    -0.06
    paren
    -0.05
    tw
    -0.05
    andra
    -0.05
    ¯¯
    -0.05
     affirm
    -0.05
    utures
    -0.05
    POSITIVE LOGITS
    çļĦåij¢
    0.08
    åłĤ
    0.07
    raig
    0.07
    egi
    0.07
    reja
    0.07
    iog
    0.07
    esak
    0.07
    alui
    0.07
    baka
    0.07
    fortun
    0.07
    Activations Density 0.322%

    No Known Activations