© 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. 24-TRANSCODER-HP
    7. 150188
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flowed
    -0.31
     кап
    -0.26
     flows
    -0.26
     sm
    -0.25
    @author
    -0.24
    èĥ¡åIJĮ
    -0.24
    +xml
    -0.24
     Old
    -0.23
    ear
    -0.23
    arf
    -0.23
    POSITIVE LOGITS
    =count
    0.31
    /orders
    0.25
    elry
    0.25
    ambique
    0.25
    иÑİ
    0.24
    ä¸ı
    0.24
    /legal
    0.24
    ',...↵
    0.24
    è¾ħ
    0.24
    WithMany
    0.24
    Activations Density 0.151%

    No Known Activations