© 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. 108720
    Prev
    Next
    INDEX
    Explanations

    WiFi network connection

    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
    æŀ¶
    -0.30
    apons
    -0.26
    strument
    -0.26
    åıijçĹħ
    -0.26
    acht
    -0.24
    .statistics
    -0.24
     refreshed
    -0.24
    amel
    -0.24
    instrument
    -0.24
    atoi
    -0.24
    POSITIVE LOGITS
    æĭ¾
    0.27
    åľ°åĽ¾
    0.27
     equally
    0.26
    å¡ŀ
    0.26
     Maps
    0.26
    maps
    0.26
     maps
    0.26
    åĺİ
    0.25
    æŁı
    0.25
    omap
    0.25
    Activations Density 0.970%

    No Known Activations