© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    software

    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
    Sum
    -0.30
     Sum
    -0.29
    r
    -0.25
    ä½Ĩæĺ¯æĪij
    -0.25
    éĩijé¢Ŀ
    -0.25
    Ùħت
    -0.25
    å¼Ĥ
    -0.25
    æ¶Ī
    -0.25
    t
    -0.25
     Strom
    -0.24
    POSITIVE LOGITS
    SystemService
    0.30
     leadership
    0.26
     UsersController
    0.25
     rods
    0.25
     combined
    0.24
    ãģĻãģ¹ãģį
    0.24
    >{@
    0.24
     TimeSpan
    0.23
     sober
    0.23
    .addTarget
    0.23
    Activations Density 0.035%

    No Known Activations