© 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. 25848
    Prev
    Next
    INDEX
    Explanations

    here is

    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
    impse
    -0.08
    ç»Ŀåľ°
    -0.08
    åĪĨæ¸ħ
    -0.08
    <|box_end|>
    -0.08
    .azure
    -0.08
    çĶ¨åĵģ
    -0.07
     Pregun
    -0.07
    .ie
    -0.07
     McGr
    -0.07
    ä»»ä½ķéĹ®é¢ĺ
    -0.07
    POSITIVE LOGITS
     tro
    0.07
    sher
    0.06
    OutOf
    0.06
     sample
    0.06
    ick
    0.06
    ç§ijæĬĢåıijå±ķæľīéĻIJåħ¬åı¸
    0.06
    yss
    0.06
    æł·æĿ¿éĹ´
    0.05
    æī©å±ķèµĦæĸĻ
    0.05
    tro
    0.05
    Activations Density 0.029%

    No Known Activations