© 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. 161664
    Prev
    Next
    INDEX
    Explanations

    weapon

    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
    iom
    -0.29
    itur
    -0.27
    nish
    -0.26
    æŀķ
    -0.25
     Benedict
    -0.25
    弦
    -0.25
     Mines
    -0.24
    erate
    -0.24
    eft
    -0.24
    èĵ¬
    -0.23
    POSITIVE LOGITS
    asu
    0.29
    çĹķ迹
    0.28
     clans
    0.28
    actical
    0.27
    atalog
    0.24
     μ
    0.24
    mun
    0.24
     valuation
    0.24
    èĢĮä¸į
    0.24
     handy
    0.24
    Activations Density 0.112%

    No Known Activations