© 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. 7865
    Prev
    Next
    INDEX
    Explanations

    math/code symbols

    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
    ëįķ
    -0.26
    odox
    -0.26
    jas
    -0.26
    çĻ¾å®¶
    -0.25
    ovich
    -0.25
    èįĴ
    -0.25
    åĴ¤
    -0.25
     ordin
    -0.25
    yi
    -0.24
    æµĴ
    -0.24
    POSITIVE LOGITS
    usi
    0.26
     spiral
    0.25
    ·»
    0.25
    æĿł
    0.25
     gag
    0.25
     scalar
    0.24
    åĪ«è¯´
    0.24
     Club
    0.23
    ards
    0.23
    atile
    0.23
    Activations Density 5.434%

    No Known Activations