© 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. 19-TRANSCODER-HP
    7. 8454
    Prev
    Next
    INDEX
    Explanations

    nearly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gable
    -0.25
     allowance
    -0.24
    inement
    -0.24
    borne
    -0.24
    based
    -0.23
    æĹ©æľŁ
    -0.23
    iciency
    -0.22
    èĩªçĦ¶èĢĮ
    -0.22
     Integrity
    -0.22
    esy
    -0.22
    POSITIVE LOGITS
    aur
    0.26
     compounded
    0.24
    ero
    0.24
    eur
    0.24
    é¦Ĩ
    0.23
     sums
    0.23
     umb
    0.23
    rit
    0.23
     dozen
    0.22
     compact
    0.22
    Activations Density 2.009%

    No Known Activations