© 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. 45634
    Prev
    Next
    INDEX
    Explanations

    variables like $t_w$, $R_p/R_s$, $N_d$, $\bar{M}_P$, $T_K$, $\hbar_{eff}$

    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
    yra
    -0.07
    çļĦç¼ĺæķħ
    -0.07
    ÑĢеменно
    -0.06
    en
    -0.06
    es
    -0.06
    nya
    -0.06
    оÑħ
    -0.06
    ism
    -0.06
    h
    -0.06
     buah
    -0.06
    POSITIVE LOGITS
    ç¯Ħ
    0.09
    èĮĥ
    0.09
    æĭīå¾·
    0.08
    伯çī¹
    0.08
    0.08
    ktor
    0.08
    lda
    0.07
    åĽĽæĺŁ
    0.07
    åħĭå°Ķ
    0.07
    tera
    0.07
    Activations Density 0.016%

    No Known Activations