© 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. 95991
    Prev
    Next
    INDEX
    Explanations

    T cells and immunity

    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
    èħIJ
    -0.27
    emodel
    -0.26
    оÑģÑĮ
    -0.26
    asu
    -0.25
     licensee
    -0.25
     yourselves
    -0.25
    .cloudflare
    -0.25
    ç¼ĵ
    -0.25
    åį¸
    -0.25
     differently
    -0.24
    POSITIVE LOGITS
    æĪIJçĨŁ
    0.30
    åļ¼
    0.29
    ç¾½
    0.27
    ransition
    0.26
     hors
    0.26
     crossover
    0.25
     readiness
    0.25
    åĬ¡å®ŀ
    0.24
    иÑĢование
    0.24
    -scroll
    0.24
    Activations Density 0.129%

    No Known Activations