© 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. 7717
    Prev
    Next
    INDEX
    Explanations

    1

    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
    oure
    -0.28
    acob
    -0.28
    onom
    -0.25
    elow
    -0.25
    brit
    -0.25
    宵
    -0.25
    ience
    -0.24
     enactment
    -0.24
    çī¢
    -0.24
    -paper
    -0.24
    POSITIVE LOGITS
    enet
    0.29
    Collections
    0.26
    è¿Ľç¨ĭ
    0.25
    æ·±æ¸Ĭ
    0.24
    æĬ¢åħĪ
    0.24
    Ñģел
    0.24
    çļĦçģµéŃĤ
    0.23
    为æĤ¨
    0.23
    æŃ£å½ĵ
    0.23
    xCA
    0.23
    Activations Density 0.071%

    No Known Activations