© 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. 23-TRANSCODER-HP
    7. 163068
    Prev
    Next
    INDEX
    Explanations

    energy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人æīį
    -0.28
    çĻ¾å®¶
    -0.28
    ist
    -0.27
    suma
    -0.26
    龸
    -0.26
    ird
    -0.25
    æķĻèĤ²
    -0.25
    eldon
    -0.25
    çļĦç¡®
    -0.25
    .future
    -0.25
    POSITIVE LOGITS
     attachment
    0.28
    attachment
    0.27
     Attachment
    0.26
     playa
    0.26
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    0.25
     inner
    0.25
    çķļ
    0.25
    unting
    0.25
    obile
    0.24
    工夫
    0.24
    Activations Density 0.009%

    No Known Activations