© 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. 12980
    Prev
    Next
    INDEX
    Explanations

    suffix ending in `ica`, `anea`, `ivo`, `ace`, `ale`, `ol`

    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
    à³įದ
    -0.08
    EFR
    -0.07
    è¿Ļä¹Īä¸Ģ个
    -0.07
    ','.
    -0.07
    åİŁåĽłå°±æĺ¯
    -0.07
    ÑħодÑĭ
    -0.07
    edur
    -0.07
    jec
    -0.07
    ulam
    -0.07
     zentr
    -0.07
    POSITIVE LOGITS
    ométr
    0.10
    ographique
    0.09
    autaire
    0.09
    oscop
    0.08
    à¹Ĩ
    0.08
    oces
    0.07
    à¸Ĺรียà¹Į
    0.07
    azionale
    0.07
    atif
    0.06
    à¸Ļà¹Į
    0.06
    Activations Density 0.079%

    No Known Activations