© 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. 108413
    Prev
    Next
    INDEX
    Explanations

    conversational/technical mix

    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
    å¶Ĥ
    -0.28
    æĺ¯ä»Ģä¹Īåij¢
    -0.28
    .dark
    -0.27
     dashes
    -0.26
    iqué
    -0.26
    ousand
    -0.26
    mÃ¤ÃŁig
    -0.26
    (filters
    -0.25
    åī¯
    -0.24
    åĢĻéĢī
    -0.24
    POSITIVE LOGITS
    æĮij
    0.32
    usu
    0.27
    avel
    0.25
    eva
    0.25
     reach
    0.25
     gre
    0.25
     lul
    0.25
     sector
    0.25
    ngr
    0.24
    æľĢ主è¦ģçļĦ
    0.24
    Activations Density 1.162%

    No Known Activations