© 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. 14430
    Prev
    Next
    INDEX
    Explanations

    academic writing and references

    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
    è®©æĽ´å¤ļ读èĢħ
    -0.08
    è¹Ħ
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    -0.07
     Senat
    -0.07
    inel
    -0.07
    į°
    -0.07
    WISE
    -0.07
    继ç»Ńéĺħ读
    -0.07
    èĪ¬åľ°
    -0.07
    POSITIVE LOGITS
    aper
    0.07
    è½½
    0.07
    hips
    0.07
    å¿ĥè¡Ģ
    0.07
    ozo
    0.07
    icles
    0.06
    ooks
    0.06
    itek
    0.06
    åĽłæŀľ
    0.06
    .qq
    0.06
    Activations Density 0.003%

    No Known Activations