© 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. 162798
    Prev
    Next
    INDEX
    Explanations

    Christian

    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
    sole
    -0.26
     wool
    -0.26
    igid
    -0.26
    pieces
    -0.25
    errupt
    -0.25
    ä½ľèĢħæľ¬äºº
    -0.25
     Crowd
    -0.25
     har
    -0.25
    ë¶
    -0.24
    aptop
    -0.24
    POSITIVE LOGITS
    æĺ¯ä½ł
    0.29
    å®ľå±ħ
    0.28
    arna
    0.28
    usta
    0.27
    æĸĩåĮĸåĴĮ
    0.26
    lke
    0.26
    è§ģæķĪ
    0.26
    TC
    0.26
    缮åīį
    0.25
    xaa
    0.24
    Activations Density 0.001%

    No Known Activations