© 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. 162936
    Prev
    Next
    INDEX
    Explanations

    banks

    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
    oler
    -0.27
     Meg
    -0.26
    Meg
    -0.25
    족
    -0.24
    idel
    -0.24
     scho
    -0.23
    åį¡çīĩ
    -0.23
    éĥ¨åī¯éĥ¨éķ¿
    -0.23
    urrencies
    -0.23
    éĥ¨
    -0.23
    POSITIVE LOGITS
     discussed
    0.55
     examined
    0.53
     studied
    0.53
     reviewed
    0.49
     tested
    0.47
     investigated
    0.45
     analysed
    0.44
     surveyed
    0.44
     analyzed
    0.44
     cited
    0.43
    Activations Density 0.003%

    No Known Activations