© 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. 23-TRANSCODER-HP
    7. 24941
    Prev
    Next
    INDEX
    Explanations

    click

    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
    olec
    -0.28
    说ä»Ģä¹Ī
    -0.26
    ude
    -0.26
    beth
    -0.26
    uled
    -0.25
    INC
    -0.25
    说è¯Ŀ
    -0.25
    å²ģæŶ
    -0.25
     initialized
    -0.25
    ãĤıãĤĮ
    -0.24
    POSITIVE LOGITS
     CLICK
    0.32
    æѤå¤Ħ
    0.32
     clicking
    0.31
     here
    0.31
     click
    0.30
    click
    0.30
    ä¸ĭéĿ¢
    0.29
    here
    0.29
    her
    0.28
     HERE
    0.28
    Activations Density 0.005%

    No Known Activations