© 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. 9280
    Prev
    Next
    INDEX
    Explanations

    instructions and technical details

    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
    å·¥åľ°
    -0.26
    CERT
    -0.26
     regression
    -0.24
    涧
    -0.24
    æľīåĪ©
    -0.24
    è¥Ħ
    -0.23
    itt
    -0.23
    ä½ľåĵģåĨħ容
    -0.23
     Luther
    -0.23
    ãģ®ãģĵãģ¨
    -0.23
    POSITIVE LOGITS
    çĮ·
    0.28
    ÑĥлÑĮ
    0.25
    大çīĩ
    0.25
     Gazette
    0.25
    atos
    0.25
     lou
    0.24
    prus
    0.24
    dating
    0.23
    注æĦıäºĭ项
    0.23
    alon
    0.23
    Activations Density 0.784%

    No Known Activations