© 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. 108662
    Prev
    Next
    INDEX
    Explanations

    scientific code

    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
    ê»ĺ
    -0.28
     contrat
    -0.28
    æĤĮ
    -0.27
     normalized
    -0.27
    æľįåĬ¡åĮº
    -0.26
    å±Ģ
    -0.25
    代åĬŀ
    -0.24
    纪
    -0.24
    ä¸Ģ次æĢ§
    -0.24
    çķ¿
    -0.24
    POSITIVE LOGITS
    imson
    0.27
    anism
    0.26
    æģ¶
    0.26
    æµĨ
    0.25
    讼
    0.25
    =com
    0.25
    etus
    0.24
    Above
    0.24
    ingham
    0.24
    íĤ·
    0.24
    Activations Density 0.058%

    No Known Activations