© 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. 24-TRANSCODER-HP
    7. 150943
    Prev
    Next
    INDEX
    Explanations

    computing and forms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -area
    -0.28
    blo
    -0.27
    reste
    -0.27
    æĢ»éĿ¢ç§¯
    -0.26
    .area
    -0.25
    /Area
    -0.25
    å¤ļä¸ªåĽ½å®¶
    -0.25
    lok
    -0.25
     area
    -0.23
    Area
    -0.23
    POSITIVE LOGITS
     season
    0.34
     Bapt
    0.31
    åŃ£
    0.31
    å¤Ħ
    0.29
    å±Ĭ
    0.29
     seasons
    0.28
    èµĽåŃ£
    0.28
    yan
    0.27
    å±Ĩ
    0.26
     pert
    0.25
    Activations Density 0.111%

    No Known Activations