© 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
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 57853
    Prev
    Next
    INDEX
    Explanations

    speed and efficiency

    np_max-act-logits · gemini-2.0-flash
    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
    å¾Īå¿«å°±
    -0.31
    BERS
    -0.30
    æ²»çIJĨä½ĵç³»
    -0.27
    æľīè¿ĩ
    -0.27
    èŀºæĹĭ
    -0.26
    gar
    -0.26
    åĬ¨çĶŁæĪIJ
    -0.24
    ç¨į
    -0.24
    ìĬ·
    -0.24
    ðŁ¤£
    -0.24
    POSITIVE LOGITS
    éħįèµĦ
    0.28
    etty
    0.28
    å¿ħè¦ģ
    0.28
    nowled
    0.27
    .yahoo
    0.26
     necessary
    0.26
    imports
    0.25
    necessary
    0.25
     oblig
    0.24
    pot
    0.24
    Activations Density 0.032%

    No Known Activations