© 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. 24-TRANSCODER-HP
    7. 150215
    Prev
    Next
    INDEX
    Explanations

    open

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$(
    -0.28
    loth
    -0.26
    æĺİæĹ¥
    -0.25
    oli
    -0.25
    athy
    -0.25
     reconsider
    -0.24
    VEC
    -0.23
    Щ
    -0.23
    apol
    -0.23
    伶
    -0.23
    POSITIVE LOGITS
    dims
    0.30
    _dimensions
    0.24
    çŃļ
    0.24
    èħĻ
    0.24
     elev
    0.23
    æīĵéĢłåĩº
    0.23
    ufe
    0.23
     delivered
    0.23
     expans
    0.23
    prises
    0.23
    Activations Density 0.130%

    No Known Activations