© 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. 9151
    Prev
    Next
    INDEX
    Explanations

    reproductive ratio, quality factor, fundamental form, diffusivity, compressibilities, permeability, relaxations

    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
    çĥģ
    -0.08
    wana
    -0.07
    ç¶ļãģį
    -0.07
    å±ħå¤ļ
    -0.07
     Galli
    -0.07
    rech
    -0.07
    cato
    -0.07
    åĬŁåºķ
    -0.06
    (","
    -0.06
    akens
    -0.06
    POSITIVE LOGITS
    ocere
    0.08
    ieu
    0.08
    evity
    0.07
    家æľī
    0.07
    avit
    0.07
    avail
    0.06
    heid
    0.06
    structor
    0.06
    avent
    0.06
    ipo
    0.06
    Activations Density 0.020%

    No Known Activations