© 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. 150375
    Prev
    Next
    INDEX
    Explanations

    child development research

    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
    ousse
    -0.26
    æĮĩ
    -0.26
    exion
    -0.26
    åıĹæįŁ
    -0.26
    æĶ¶åĪ°
    -0.25
    å°ıæŶåīį
    -0.25
     resisted
    -0.24
    thouse
    -0.24
     Refer
    -0.24
     alerted
    -0.24
    POSITIVE LOGITS
    æ¯į
    0.29
    .setParent
    0.29
    plevel
    0.29
    ë³ij
    0.26
    enity
    0.25
    å¹²åĩĢ
    0.25
     лиÑĨ
    0.25
    Mother
    0.25
    ographs
    0.25
    绣é¢Ĩ
    0.24
    Activations Density 0.111%

    No Known Activations