© 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. 150007
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
    piring
    -0.28
    amar
    -0.28
     Assembly
    -0.27
    eteria
    -0.26
    burger
    -0.26
     neighbouring
    -0.26
    amu
    -0.25
     Gareth
    -0.25
     neighbours
    -0.25
    pired
    -0.25
    POSITIVE LOGITS
     dose
    0.31
     doses
    0.27
     dip
    0.26
     przec
    0.26
     dos
    0.26
     middle
    0.26
    è¡¥
    0.25
    礼
    0.25
    ź
    0.25
    ale
    0.25
    Activations Density 0.006%

    No Known Activations