© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 266
    Prev
    Next
    INDEX
    Explanations

    drying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucket
    -0.31
     Jonas
    -0.27
    adan
    -0.27
    åĺīå¹´
    -0.26
    éĢļé£İ
    -0.26
    arial
    -0.26
    æıIJ款
    -0.25
    –and
    -0.24
    åµ
    -0.24
    ).__
    -0.24
    POSITIVE LOGITS
    æ´¹
    0.29
     backward
    0.29
    Back
    0.28
    åĻ«
    0.27
     onto
    0.25
     interface
    0.25
    er
    0.25
     backwards
    0.24
    æĺİãĤīãģĭ
    0.24
     while
    0.24
    Activations Density 0.130%

    No Known Activations