© 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. 163098
    Prev
    Next
    INDEX
    Explanations

    tab

    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
     Extr
    -0.25
    iteit
    -0.25
    ivities
    -0.25
    ividad
    -0.24
     Peer
    -0.24
    EAR
    -0.23
     ster
    -0.23
    æ£į
    -0.23
     Kumar
    -0.23
     extr
    -0.23
    POSITIVE LOGITS
    azine
    0.31
    å®ŀæĻ¯
    0.26
    rolling
    0.25
    afil
    0.25
    quot
    0.25
    wheel
    0.24
    çĨŁç»ĥ
    0.24
    tle
    0.24
    ulations
    0.24
     lookup
    0.24
    Activations Density 0.398%

    No Known Activations