© 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. 64161
    Prev
    Next
    INDEX
    Explanations

    degree modifiers

    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
    ä¸Ńåħ·æľī
    -0.07
     rank
    -0.07
     Ribe
    -0.07
     ranked
    -0.07
    —at
    -0.07
     Rank
    -0.06
    ä¸įä»ħèĥ½
    -0.06
    å°½åı¯èĥ½åľ°
    -0.06
    ä»¿ä½Ľæĺ¯
    -0.06
    çĮĽçĦ¶
    -0.06
    POSITIVE LOGITS
    éļĻ
    0.07
    天å¤ĸ
    0.07
    verso
    0.07
    nike
    0.07
    åıĹçĸ«æĥħå½±åĵį
    0.06
    _then
    0.06
    éģĹæĨ¾çļĦæĺ¯
    0.06
    gun
    0.06
    snd
    0.06
    ä½Ĩè¿ĺæĺ¯
    0.06
    Activations Density 0.002%

    No Known Activations