© 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. 107578
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ÑĤон
    -0.26
     complement
    -0.25
    ORAGE
    -0.25
    orman
    -0.24
    ptron
    -0.24
    è¡¥åħħ
    -0.24
    lining
    -0.24
    å¨ĺ
    -0.24
    éĺ¿
    -0.24
    æĸ¹ä¾¿
    -0.24
    POSITIVE LOGITS
    quo
    0.28
    _VARIABLE
    0.26
    _yield
    0.25
    {}{↵
    0.25
    ObjectContext
    0.25
     crypt
    0.25
    _DP
    0.24
    antium
    0.24
    äºĭæķħåıijçĶŁ
    0.24
    orio
    0.24
    Activations Density 0.141%

    No Known Activations

    This feature has no known activations.