© 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. 161847
    Prev
    Next
    INDEX
    Explanations

    location

    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
    家ä¼ģä¸ļ
    -0.29
    èĢĮæĺ¯
    -0.28
    éĩĩæijĺ
    -0.28
    mes
    -0.27
    semblies
    -0.26
    appa
    -0.26
    个人
    -0.26
    ä¸ĢèĦļ
    -0.25
    RK
    -0.25
    .den
    -0.25
    POSITIVE LOGITS
     of
    0.31
     hell
    0.30
    /place
    0.28
    ally
    0.28
    _sur
    0.27
    -neutral
    0.27
    SUR
    0.27
    /type
    0.26
    /activity
    0.26
     and
    0.25
    Activations Density 0.235%

    No Known Activations