© 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. 154
    Prev
    Next
    INDEX
    Explanations

    ized

    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
    anford
    -0.29
    ç§ģæľį
    -0.29
    inidad
    -0.27
    sampling
    -0.27
    -exc
    -0.26
    æĹłç¼ĺ
    -0.25
    zug
    -0.25
    nor
    -0.25
    inic
    -0.24
    roit
    -0.24
    POSITIVE LOGITS
     wor
    0.26
    ÑģÑĤво
    0.25
    thes
    0.25
     FBI
    0.25
     Rice
    0.25
    mine
    0.24
    éĥİ
    0.23
    hen
    0.23
    riet
    0.23
    åĩĿèģļ
    0.23
    Activations Density 0.028%

    No Known Activations