© 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. 22-TRANSCODER-HP
    7. 88054
    Prev
    Next
    INDEX
    Explanations

    -letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corona
    -0.30
    .cg
    -0.25
     sinc
    -0.25
    ipi
    -0.24
    èģª
    -0.24
    å¹¢
    -0.23
    č↵↵
    -0.23
    åĨįåİ»
    -0.23
    destruct
    -0.23
    :)↵
    -0.23
    POSITIVE LOGITS
    refs
    0.27
     reckon
    0.27
    otec
    0.24
    稳妥
    0.24
     fseek
    0.24
    æľīåħ´è¶£
    0.24
    èģĭ
    0.23
     em
    0.23
    _initialized
    0.23
    ndl
    0.23
    Activations Density 0.002%

    No Known Activations