© 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. 6667
    Prev
    Next
    INDEX
    Explanations

    Integrated, comprehensive approaches

    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
    èŃīæĺİ
    -0.30
    ä¸ĢåĪĩéĥ½
    -0.25
    æīª
    -0.24
    ä¸įçĦ¶
    -0.24
    undi
    -0.24
    tti
    -0.24
    heck
    -0.24
    zM
    -0.24
    ifice
    -0.24
    åįķ纯çļĦ
    -0.23
    POSITIVE LOGITS
     dip
    0.26
    æ¤Ĵ
    0.26
     joint
    0.25
     nh
    0.25
     preferred
    0.25
     sed
    0.25
     Joint
    0.25
    sta
    0.24
     global
    0.24
     coupling
    0.24
    Activations Density 0.045%

    No Known Activations