© 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. 25-TRANSCODER-HP
    7. 108508
    Prev
    Next
    INDEX
    Explanations

    studio album

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rever
    -0.30
    å¤įå·¥
    -0.28
    led
    -0.26
    座è°Īä¼ļ
    -0.25
    -of
    -0.24
    ansom
    -0.24
    SetTitle
    -0.23
     bod
    -0.23
    UCT
    -0.23
    æīĵæĸŃ
    -0.23
    POSITIVE LOGITS
    _TestCase
    0.26
    åģ¥åº·çļĦ
    0.24
    å°ģ
    0.24
    次
    0.23
     merchandise
    0.23
    inalg
    0.23
     apis
    0.23
     CHR
    0.23
    disposing
    0.22
    /copyleft
    0.22
    Activations Density 1.637%

    No Known Activations