© 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. 33-TRANSCODER-HP
    7. 52928
    Prev
    Next
    INDEX
    Explanations

    extra

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİ»çľĭ
    -0.27
    å¼ĢåºĹ
    -0.27
     pil
    -0.27
     soup
    -0.26
    _soup
    -0.26
     straight
    -0.26
    _uniform
    -0.25
     shine
    -0.25
     upright
    -0.24
     northwest
    -0.24
    POSITIVE LOGITS
     class
    0.29
    :class
    0.28
    .class
    0.28
    acher
    0.27
     clase
    0.27
    Ac
    0.26
    Mind
    0.26
     (~(
    0.26
    rlen
    0.26
    <Class
    0.26
    Activations Density 0.004%

    No Known Activations