© 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. 108269
    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
    haps
    -0.27
    ackers
    -0.26
    楽
    -0.26
    rets
    -0.26
    åij½åIJį
    -0.25
    åİŁæĿ¥
    -0.24
     kısm
    -0.24
    ftar
    -0.23
    éĶij
    -0.23
    ÑĤели
    -0.23
    POSITIVE LOGITS
    .iterator
    0.28
    áo
    0.28
    Liter
    0.26
    *c
    0.25
    åĪ¶åº¦
    0.24
     Liter
    0.24
    èµ·é£ŀ
    0.23
    ä¾Ŀæ³ķ
    0.23
    sen
    0.23
    è¼Ķ
    0.23
    Activations Density 2.436%

    No Known Activations

    This feature has no known activations.