© 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. 162767
    Prev
    Next
    INDEX
    Explanations

    scientific/technical processes

    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
    æĿĥåĪ©
    -0.29
    <tr
    -0.27
    !--
    -0.25
     Mell
    -0.25
     Rights
    -0.25
     Rally
    -0.24
     Bau
    -0.24
    çļĦæĿĥåĪ©
    -0.24
    ACCOUNT
    -0.23
    æ¬ĬåĪ©
    -0.23
    POSITIVE LOGITS
    -wise
    0.28
     materia
    0.28
    å¢ģ
    0.27
     matière
    0.27
    -dependent
    0.26
     material
    0.26
    è¦ģ害
    0.26
    -fed
    0.25
    -linked
    0.25
     folding
    0.25
    Activations Density 0.053%

    No Known Activations