© 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. 3635
    Prev
    Next
    INDEX
    Explanations

    end-of-word suffixes or specific nouns

    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
    çłĶ
    -0.08
    sequ
    -0.08
    nan
    -0.07
    oth
    -0.07
    enze
    -0.07
    _attention
    -0.07
    ayed
    -0.07
    端
    -0.07
    agina
    -0.06
    åĴĮè¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
    -like
    0.09
    -ish
    0.08
    _candidate
    0.08
     disguised
    0.08
    åħ¼
    0.07
    çĻ»è®°è¯ģ
    0.07
    _formatter
    0.07
    ehl
    0.07
     candidate
    0.07
    ernel
    0.07
    Activations Density 0.198%

    No Known Activations