© 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. 30-TRANSCODER-HP
    7. 96714
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     divide
    -0.27
    drop
    -0.26
     sit
    -0.25
    larını
    -0.25
     Khan
    -0.25
     relate
    -0.25
     pet
    -0.24
    ılm
    -0.24
    åıijå±ķæł¼å±Ģ
    -0.24
     accordingly
    -0.24
    POSITIVE LOGITS
    ä½ķ
    0.36
     What
    0.34
     Why
    0.33
     Issues
    0.30
     Another
    0.29
     Vision
    0.29
     Reflection
    0.29
     Part
    0.28
     Version
    0.28
     Who
    0.28
    Activations Density 0.152%

    No Known Activations