© 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. 19-TRANSCODER-HP
    7. 6140
    Prev
    Next
    INDEX
    Explanations

    arm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.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¸įåı¯æĢĿ
    -0.26
    rpm
    -0.25
    bpp
    -0.25
    cipher
    -0.24
    eer
    -0.24
    ä¸įçŁ¥ä¸į
    -0.24
    ä¸įçķĻ
    -0.23
     anon
    -0.23
    æ·ĺæ±°
    -0.23
    æ¸ħæ¥ļ
    -0.23
    POSITIVE LOGITS
    lessly
    0.30
    less
    0.28
     latter
    0.27
    og
    0.26
    åĬ³
    0.26
     minimum
    0.24
     current
    0.24
    chair
    0.24
    asses
    0.23
    sworth
    0.23
    Activations Density 1.616%

    No Known Activations