© 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. 95497
    Prev
    Next
    INDEX
    Explanations

    K

    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
    flu
    -0.27
    rens
    -0.26
    >|
    -0.25
    åĪĩãĤĮ
    -0.25
    éĿĴ
    -0.24
    cej
    -0.24
     BEN
    -0.23
    black
    -0.23
    اخت
    -0.23
    ben
    -0.23
    POSITIVE LOGITS
    é¡ĺ
    0.26
    wine
    0.26
    kos
    0.26
    lace
    0.26
    ACA
    0.25
    æ·¹
    0.25
    persist
    0.24
    ICA
    0.24
    iÄĩ
    0.24
    æŶä¸į
    0.24
    Activations Density 0.882%

    No Known Activations