© 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. 162986
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    eer
    -0.30
    avax
    -0.28
    osal
    -0.27
    ume
    -0.26
    pen
    -0.26
    ee
    -0.26
    ose
    -0.25
    ona
    -0.25
    phony
    -0.25
    hips
    -0.25
    POSITIVE LOGITS
    è£Ĥ
    0.26
     Discovery
    0.26
    _PAGES
    0.25
    éĻ¨
    0.25
    scratch
    0.25
    å©´
    0.25
    Squared
    0.24
     stirred
    0.24
     discovery
    0.24
     Intervention
    0.24
    Activations Density 0.001%

    No Known Activations