© 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. 8802
    Prev
    Next
    INDEX
    Explanations

    first

    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
    éĢĶ
    -0.31
    计åĪĴ
    -0.27
    éģĵè·¯ä¸Ĭ
    -0.25
    è¨ĪåĬĥ
    -0.25
    Provide
    -0.25
     CreateMap
    -0.25
     Partnership
    -0.24
     foundations
    -0.24
    vez
    -0.24
     Plan
    -0.24
    POSITIVE LOGITS
     concrete
    0.30
    ãģĹãģŁãģĵãģ¨
    0.27
    ä¹ĭä½ľ
    0.27
    æĪĸå¤ļ
    0.26
     coating
    0.25
    bie
    0.24
    inel
    0.24
    ency
    0.24
    itet
    0.24
    ãĥľãĥ¼ãĥī
    0.24
    Activations Density 0.041%

    No Known Activations