© 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. 162751
    Prev
    Next
    INDEX
    Explanations

    persecution, oppression

    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
    though
    -0.27
    å·¥ç¨ĭæĬĢæľ¯
    -0.26
     spo
    -0.26
    rang
    -0.26
     Fever
    -0.25
    éĽ¢ãĤĮ
    -0.24
     Blind
    -0.24
     Delta
    -0.24
    Split
    -0.23
     Nimbus
    -0.23
    POSITIVE LOGITS
    æīĵåİĭ
    0.28
    resses
    0.28
     torture
    0.26
     sentencing
    0.25
    ]>
    0.25
     denounced
    0.25
     envy
    0.25
    ç»Ħç»ĩå¼Ģå±ķ
    0.25
     awaited
    0.25
    -issue
    0.24
    Activations Density 0.006%

    No Known Activations