© 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. 108503
    Prev
    Next
    INDEX
    Explanations

    about

    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
    este
    -0.28
    èĴ¯
    -0.28
    och
    -0.27
     plast
    -0.27
     overd
    -0.26
    注æĺİ
    -0.26
    绵
    -0.25
    çĸ¯
    -0.25
    inne
    -0.25
    eea
    -0.25
    POSITIVE LOGITS
    åĪļåĪļ
    0.57
    åĪļ
    0.50
    åį³å°Ĩ
    0.49
    æŃ£åľ¨
    0.44
     recently
    0.42
    ä¸įä¹ħ
    0.39
     imminent
    0.38
     soon
    0.38
    åīĽ
    0.38
     about
    0.38
    Activations Density 1.277%

    No Known Activations