© 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. 95945
    Prev
    Next
    INDEX
    Explanations

    for

    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
     jou
    -0.28
    _brand
    -0.25
     Objects
    -0.25
    åı£å¾Ħ
    -0.25
     chemicals
    -0.25
    åħ±åIJĮåıijå±ķ
    -0.25
    临æŶ
    -0.25
     ambigu
    -0.24
     Brands
    -0.23
    .getObject
    -0.23
    POSITIVE LOGITS
     home
    0.28
    æĪ¶
    0.27
     fill
    0.26
    verture
    0.26
    kle
    0.25
     distance
    0.25
    chemes
    0.25
    olini
    0.25
    ALLE
    0.25
     Fill
    0.24
    Activations Density 0.883%

    No Known Activations