© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 143
    Prev
    Next
    INDEX
    Explanations

    bacteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è´¬
    -0.27
    :before
    -0.27
    å¡Ķ
    -0.26
    nah
    -0.26
    ublic
    -0.26
    одеÑĢж
    -0.25
     prior
    -0.25
     pri
    -0.24
    çĵ¢
    -0.24
    ocache
    -0.24
    POSITIVE LOGITS
     IDD
    0.28
     unst
    0.26
    ogenic
    0.25
    å°ıçĭĹ
    0.25
    è¿ĽéŨ
    0.24
    UNG
    0.24
    宣è¨Ģ
    0.24
     PSU
    0.24
    abilidad
    0.23
     fond
    0.23
    Activations Density 0.066%

    No Known Activations