© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8690
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Invariant
    -0.28
    ermen
    -0.26
     remin
    -0.25
    ån
    -0.25
     unnamed
    -0.25
    ISP
    -0.25
     ambient
    -0.25
    ãĤ¯ãĥŃ
    -0.25
    .effects
    -0.25
    asma
    -0.24
    POSITIVE LOGITS
    èī¯
    0.30
    çł´ç¢İ
    0.27
    ç¥ŀ
    0.27
    èĦĨ
    0.26
    èĮ¸
    0.25
    ç¢İçīĩ
    0.25
    èī¯å¥½
    0.25
    æģIJ
    0.25
     Qatar
    0.25
    (sound
    0.24
    Activations Density 0.000%

    No Known Activations