© 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. 161805
    Prev
    Next
    INDEX
    Explanations

    can

    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
    åįĸç»Ļ
    -0.28
    æ¯ıæ¯ı
    -0.26
    è¾ĵç»Ļ
    -0.26
    dpi
    -0.25
     Crime
    -0.25
    .gg
    -0.24
    itime
    -0.24
    _ASSUME
    -0.24
     stole
    -0.24
    south
    -0.24
    POSITIVE LOGITS
    w
    0.30
     Criteria
    0.28
     arbitrary
    0.28
     optionally
    0.26
     need
    0.26
    het
    0.26
    ä»»æĦı
    0.26
     pure
    0.25
     criteria
    0.25
    wis
    0.25
    Activations Density 0.009%

    No Known Activations