© 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. 64048
    Prev
    Next
    INDEX
    Explanations

    list keys (like name, id, number)

    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
    pon
    -0.08
    ¹Ħ
    -0.07
    åIJĪåIJĮ约å®ļ
    -0.07
    los
    -0.07
    arani
    -0.06
    berger
    -0.06
    èģĨ
    -0.06
    ancell
    -0.06
    boro
    -0.06
    åį³åĪ°
    -0.06
    POSITIVE LOGITS
    Inflater
    0.08
    éĶ®
    0.08
    aye
    0.08
    å°½éĩıå°ij
    0.08
    ç»ĵæŀĦç®Ģåįķ
    0.07
    ziem
    0.07
    éįµ
    0.07
    æł¹æį®æĿĥåĪ©è¦ģæ±Ĥ
    0.07
    edImage
    0.07
    -Allow
    0.07
    Activations Density 0.048%

    No Known Activations