© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11724
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    ↵↵
    -0.06
    ement
    -0.06
    çĦ¶åIJİçĤ¹åĩ»
    -0.06
    ements
    -0.06
                    ↵↵
    -0.06
    çĦ¶åIJİåľ¨
    -0.06
            ↵↵
    -0.06
    ation
    -0.06
    rze
    -0.06
     Goose
    -0.06
    POSITIVE LOGITS
    åħ¬åı·
    0.09
    ologista
    0.08
    긴
    0.08
    WithValue
    0.08
    OLOGIA
    0.08
    ()}
    0.08
    InputModule
    0.07
    ówka
    0.07
     Ñıке
    0.07
     eksk
    0.07
    Activations Density 0.203%

    No Known Activations