© 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. 14-TRANSCODER-HP
    7. 40282
    Prev
    Next
    INDEX
    Explanations

    touch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
            ↵        ↵        ↵
    -0.27
     апп
    -0.26
     advent
    -0.25
    è¿ľè¿ľ
    -0.25
     databases
    -0.24
    çĥĽ
    -0.24
    ä¸į论æĺ¯
    -0.24
     Äijá»ģ
    -0.24
    çħ²
    -0.24
    _APPEND
    -0.24
    POSITIVE LOGITS
     slips
    0.29
    æij©æĵ¦
    0.27
    AccessException
    0.27
     interchange
    0.26
    .asp
    0.26
    ilarity
    0.26
    åī²
    0.25
     friction
    0.25
    æľªæĪIJ
    0.25
     seizing
    0.25
    Activations Density 1.294%

    No Known Activations