© 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. 46
    Prev
    Next
    INDEX
    Explanations

    ins

    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
    èį·
    -0.27
    缺
    -0.27
    HOOK
    -0.26
    å½ĵä¸Ń
    -0.26
    idel
    -0.26
    isos
    -0.25
    stitute
    -0.25
    èIJ½åı¶
    -0.24
    åºķ
    -0.24
    .setSelection
    -0.24
    POSITIVE LOGITS
    eguard
    0.27
    avings
    0.27
    主æĴŃ
    0.26
     begr
    0.26
    .asm
    0.25
    åĨħå¤ĸ
    0.24
    ç»ıæµİä½ĵ
    0.24
     lex
    0.24
    åĨĽäºº
    0.24
    upyter
    0.23
    Activations Density 0.019%

    No Known Activations