© 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. 150249
    Prev
    Next
    INDEX
    Explanations

    Code/programming snippets

    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
    roid
    -0.29
    .bundle
    -0.28
    rench
    -0.26
    Ñijм
    -0.26
    DM
    -0.26
    amiliar
    -0.25
     jointly
    -0.24
    åĽ½äºº
    -0.23
    neys
    -0.23
    hit
    -0.23
    POSITIVE LOGITS
    ocate
    0.28
    arnation
    0.27
    InstanceState
    0.26
    overe
    0.26
    èIJ¥
    0.26
    ite
    0.26
    еле
    0.25
     OnTriggerEnter
    0.25
    ITED
    0.25
    oned
    0.25
    Activations Density 0.082%

    No Known Activations