© 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. 23-TRANSCODER-HP
    7. 162973
    Prev
    Next
    INDEX
    Explanations

    .&

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erk
    -0.25
     fil
    -0.25
    ood
    -0.24
    cript
    -0.23
    er
    -0.23
    -scale
    -0.22
    oods
    -0.22
    .printStackTrace
    -0.22
    аз
    -0.22
    itt
    -0.21
    POSITIVE LOGITS
    tempt
    0.25
    è¿«
    0.25
    око
    0.25
    Assembler
    0.24
     metic
    0.24
    è¡£æŁľ
    0.24
    hta
    0.23
    磧
    0.23
    ä¼ļéķ¿
    0.22
     cautioned
    0.22
    Activations Density 0.095%

    No Known Activations