© 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. 108006
    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
    udge
    -0.33
    osten
    -0.28
    avery
    -0.27
     erh
    -0.25
    aleza
    -0.25
     syndrome
    -0.25
    ajes
    -0.24
     propósito
    -0.24
     Syndrome
    -0.24
    ingen
    -0.24
    POSITIVE LOGITS
     назад
    0.26
     eventually
    0.26
    ä½łå°±
    0.25
    .Double
    0.24
    éĵ§
    0.24
     ساب
    0.24
    ä¸ĩæĪ·
    0.24
    segments
    0.24
     PG
    0.24
    _ck
    0.23
    Activations Density 1.142%

    No Known Activations

    This feature has no known activations.