© 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. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96258
    Prev
    Next
    INDEX
    Explanations

    personal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropic
    -0.27
    quina
    -0.25
    çµ·
    -0.24
    istics
    -0.24
    atern
    -0.24
    åĬ£
    -0.24
    reat
    -0.24
    åİĦ
    -0.24
    tplib
    -0.23
    ½Ķ
    -0.23
    POSITIVE LOGITS
    个人
    1.72
     personal
    1.62
    personal
    1.39
    åĢĭ人
    1.39
     Personal
    1.38
    Personal
    1.32
     individual
    1.30
    åĴĮ个人
    1.29
    个ä½ĵ
    1.25
    _personal
    1.18
    Activations Density 1.306%

    No Known Activations