© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7467
    Prev
    Next
    INDEX
    Explanations

    code or logs

    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
    ä¸Ģ个éĹ®é¢ĺ
    -0.29
     indoors
    -0.28
    产
    -0.26
    åħŃå¹´
    -0.25
    ãģ¦
    -0.25
    çĶ¢
    -0.25
    çĽijè§Ĩ
    -0.25
     em
    -0.24
    tls
    -0.24
    anja
    -0.24
    POSITIVE LOGITS
     totaled
    0.28
    踮
    0.27
    翻身
    0.27
    orney
    0.25
    æľīæĽ´å¥½çļĦ
    0.25
    è¾Ĺ
    0.25
     Everest
    0.25
    Been
    0.25
    åı¨
    0.25
     Excell
    0.25
    Activations Density 0.001%

    No Known Activations