© 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. 108147
    Prev
    Next
    INDEX
    Explanations

    rotary

    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
    /ad
    -0.29
    åĨ¶éĩij
    -0.27
     Lesser
    -0.26
    éĤ£äºº
    -0.24
    åĮ»çĶ¨
    -0.24
    åŃļ
    -0.24
    (TR
    -0.24
    åIJij举
    -0.23
    ordinary
    -0.23
     clearfix
    -0.23
    POSITIVE LOGITS
    alion
    0.28
    osc
    0.28
    terdam
    0.27
     inconsist
    0.27
    ilibrium
    0.26
    Club
    0.25
    elay
    0.25
    -spin
    0.25
    ))[
    0.25
    OSC
    0.25
    Activations Density 1.598%

    No Known Activations