© 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. 161855
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éľĢè¦ģçĶ¨
    -0.30
    æŁ¬
    -0.29
    æĦıæĥ³ä¸įåĪ°
    -0.27
    ế
    -0.26
    éĥ½éľĢè¦ģ
    -0.25
    geme
    -0.25
    zza
    -0.25
    _dec
    -0.24
    oug
    -0.24
     haz
    -0.24
    POSITIVE LOGITS
    rowing
    0.29
    ÑĢеÑģ
    0.28
    山路
    0.27
    jec
    0.25
    ÑĤÑĥÑĢ
    0.24
    ç±³ç²ī
    0.23
    EOF
    0.23
    ÑĢова
    0.23
    ******č↵
    0.23
    宣
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.