© 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. 108432
    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
    oken
    -0.27
    衾
    -0.26
    ENTRY
    -0.26
    _TRY
    -0.25
    _unique
    -0.24
    íĻľ
    -0.24
     decision
    -0.24
     Braun
    -0.24
    rome
    -0.24
    èĦĨ
    -0.24
    POSITIVE LOGITS
     rabbit
    0.27
    æĿ¥ä¸įåıĬ
    0.27
    ouri
    0.27
     Diamond
    0.26
    éĴ»çŁ³
    0.26
    éĩijåĪļ
    0.25
    鸳
    0.24
    diamond
    0.24
    GROUND
    0.24
    oteric
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.