© 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. 32435
    Prev
    Next
    INDEX
    Explanations

    altering state or structure

    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
    anel
    -0.09
    iams
    -0.08
    ableView
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    ijľ
    -0.08
    ços
    -0.08
    ä¾Ŀæ³ķèĩªä¸»
    -0.08
    å¤įåIJĪåŀĭ
    -0.08
    opan
    -0.07
    çĪ±å²Ĺ
    -0.07
    POSITIVE LOGITS
    åħ¶éģĵ
    0.06
     Eu
    0.06
    æľŁ
    0.06
    大æŀ£
    0.06
    roh
    0.05
     into
    0.05
    åħļè§Ħ
    0.05
    ãĤĭãĤĪãģĨãģ«
    0.05
    way
    0.05
     via
    0.05
    Activations Density 0.005%

    No Known Activations