© 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. 149614
    Prev
    Next
    INDEX
    Explanations

    Time and availability

    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
    ermen
    -0.28
    esz
    -0.27
    uncia
    -0.25
    ä½ĨæĪij
    -0.24
    .mx
    -0.24
     succeeded
    -0.24
    TÃľ
    -0.24
     OSX
    -0.24
    _caps
    -0.23
    äm
    -0.23
    POSITIVE LOGITS
    opol
    0.26
    illard
    0.24
    explo
    0.24
     Birch
    0.24
    -save
    0.24
    åİĭ缩
    0.23
    ogan
    0.23
    opro
    0.23
    open
    0.23
    ÙĥÙģ
    0.22
    Activations Density 0.277%

    No Known Activations