© 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. 57730
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
    å®ŀéĻħæĥħåĨµ
    -0.33
    itudes
    -0.30
     actual
    -0.30
    actual
    -0.30
    lemen
    -0.29
    veillance
    -0.28
    åħ·ä½ĵæĥħåĨµ
    -0.28
    ivable
    -0.28
    utan
    -0.26
    éģĤ
    -0.26
    POSITIVE LOGITS
    ç¬ŀ
    0.25
     about
    0.25
    åĮħåIJ«
    0.24
    åħ³äºİæĪij们
    0.24
    ABOUT
    0.24
     prompts
    0.23
    _about
    0.23
    æĸijæĸĵ
    0.23
    带
    0.23
     pant
    0.23
    Activations Density 0.012%

    No Known Activations