© 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. 150632
    Prev
    Next
    INDEX
    Explanations

    caption

    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
     '%$
    -0.28
    æŁĦ
    -0.27
    -0.24
    preview
    -0.24
    ä¸ĵåĮº
    -0.23
    sterdam
    -0.23
    hiba
    -0.23
     Northeast
    -0.23
    -cond
    -0.23
    ä¹Ŀé¾Ļ
    -0.22
    POSITIVE LOGITS
    ible
    0.29
    able
    0.28
    ing
    0.27
     recal
    0.25
    ira
    0.25
    orgen
    0.25
    PostBack
    0.24
    èijĽ
    0.24
    è¯ī
    0.24
    .pl
    0.24
    Activations Density 0.714%

    No Known Activations