© 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. 11873
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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
    æµ·ä¸ľ
    -0.07
    yon
    -0.07
    对äºİæĪij们
    -0.07
    resta
    -0.07
    пле
    -0.07
     prosp
    -0.07
    soon
    -0.07
     Pf
    -0.07
    olla
    -0.07
    arro
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.07
    ç¦ıçĶ°
    0.07
    éļıåľ°
    0.07
    __$
    0.06
     appunto
    0.06
    åĴ«
    0.06
    ä»ħæѤ
    0.06
    ertia
    0.06
    `.
    0.06
    æĹłæĦıéĹ´
    0.06
    Activations Density 0.039%

    No Known Activations