© 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. 30-TRANSCODER-HP
    7. 95406
    Prev
    Next
    INDEX
    Explanations

    Snippets of longer text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     possible
    -0.28
    minster
    -0.28
    éĺ³åĮº
    -0.26
    iggers
    -0.26
    бо
    -0.25
    neys
    -0.25
    lator
    -0.25
    æİ°
    -0.24
    ernel
    -0.24
    mts
    -0.24
    POSITIVE LOGITS
    èĩ³ä¸Ĭ
    0.28
     abroad
    0.28
     around
    0.27
    èĩ³æѤ
    0.27
    aat
    0.27
     which
    0.26
    å½¢æĪIJçļĦ
    0.26
    æĹ¶ç©º
    0.26
     when
    0.26
    aten
    0.26
    Activations Density 0.029%

    No Known Activations