© 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. 18-TRANSCODER-HP
    7. 89161
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     self
    -0.28
    èµĦæºIJ
    -0.27
    楼ä¸ĭ
    -0.27
     exc
    -0.26
    itous
    -0.26
    åĤ¨èĵĦ
    -0.25
    าà¸ĩ
    -0.24
     Ãĸn
    -0.24
    rok
    -0.24
    ä¸į解
    -0.24
    POSITIVE LOGITS
    èĪĴ
    0.27
    æĺ§
    0.26
    [System
    0.25
    人å¿ĥ
    0.25
    Associ
    0.25
     Ja
    0.25
    umas
    0.24
    pressed
    0.24
    VisualStyle
    0.24
    -controls
    0.24
    Activations Density 8.688%

    No Known Activations