© 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. 57672
    Prev
    Next
    INDEX
    Explanations

    Detects titles or beginnings

    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
     lucky
    -0.27
     fortunate
    -0.27
     rather
    -0.27
    echo
    -0.27
     forum
    -0.26
     echo
    -0.26
    cccc
    -0.26
    Forum
    -0.26
     room
    -0.25
     anale
    -0.25
    POSITIVE LOGITS
    ModelError
    0.30
    æĵħ
    0.26
     Pars
    0.26
    ä»»ä½ķæŶåĢĻ
    0.26
    uze
    0.26
     pose
    0.25
    agnostics
    0.25
    -operator
    0.25
     '').
    0.24
    pose
    0.24
    Activations Density 0.000%

    No Known Activations