© 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. 356
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ä¸įåħ·å¤ĩ
    -0.28
    weep
    -0.27
    è®®
    -0.26
    å¤¸å¼ł
    -0.25
     dict
    -0.24
    lok
    -0.23
    人åı£
    -0.23
    mir
    -0.23
     Dict
    -0.22
    stakes
    -0.22
    POSITIVE LOGITS
    elier
    0.29
    OTE
    0.27
     '..',
    0.26
    RES
    0.25
    č↵↵
    0.25
    Outer
    0.24
    azi
    0.24
    stem
    0.23
    #error
    0.23
    ERY
    0.23
    Activations Density 4.703%

    No Known Activations