© 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. 39815
    Prev
    Next
    INDEX
    Explanations

    mathematical substitution values

    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
    çĨŁæĤīçļĦ
    -0.08
    ç¿Ł
    -0.08
     dags
    -0.08
    semb
    -0.08
     descont
    -0.08
    erti
    -0.07
    antara
    -0.07
    adem
    -0.07
    æĸ°åĨłèĤºçĤİçĸ«æĥħ
    -0.07
    ç°¸
    -0.07
    POSITIVE LOGITS
     values
    0.07
     substitutions
    0.06
    代åħ¥
    0.06
     substitution
    0.06
     substituted
    0.06
    åĪĿå§ĭ
    0.06
    oen
    0.06
    å¦Ĥåħ¶
    0.06
     substitute
    0.06
     value
    0.06
    Activations Density 0.028%

    No Known Activations