© 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. 107955
    Prev
    Next
    INDEX
    Explanations

    Technology and internet discussions

    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
    jected
    -0.30
    åĮºåĪ«
    -0.28
    æĻĮ
    -0.27
    åĬ£åĬ¿
    -0.26
    ä¹ĭæŶ
    -0.26
    cursor
    -0.25
    祧
    -0.24
    æĵį纵
    -0.24
    dv
    -0.24
    課
    -0.24
    POSITIVE LOGITS
     crowds
    0.30
     cybersecurity
    0.28
    redd
    0.27
    覺
    0.27
     scouting
    0.27
    дал
    0.27
    è§ī
    0.26
     middleware
    0.26
    ius
    0.26
     scr
    0.26
    Activations Density 0.909%

    No Known Activations