© 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. 20591
    Prev
    Next
    INDEX
    Explanations

    adjacent groups

    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
    ä½łéĥ½
    -0.07
    ibas
    -0.07
     rel
    -0.07
    ç¬Ĩ
    -0.06
    åħ¶è§ĤçĤ¹
    -0.06
    åĭĩå¾Ģ缴åīį
    -0.06
     say
    -0.06
    rawer
    -0.06
     accordingly
    -0.06
    æŀĩ
    -0.06
    POSITIVE LOGITS
     dangling
    0.08
    stv
    0.07
    atform
    0.07
    æĪĸ缺
    0.07
     liberated
    0.07
    æı®
    0.07
     donated
    0.07
    -react
    0.07
    夺åıĸ
    0.07
     lone
    0.07
    Activations Density 0.059%

    No Known Activations