© 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. 58014
    Prev
    Next
    INDEX
    Explanations

    to

    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
    ç¼ĵ解
    -0.28
    è±ģ
    -0.27
    ollapsed
    -0.26
    endas
    -0.26
    enda
    -0.26
     ApplicationController
    -0.26
    zers
    -0.24
    è°ĥæķ´
    -0.23
    reopen
    -0.23
    å¿Ĵ
    -0.23
    POSITIVE LOGITS
    带
    0.36
     Contains
    0.36
     bear
    0.35
     contain
    0.35
     contains
    0.34
     bears
    0.33
    contains
    0.32
    åIJ«æľī
    0.32
    è½½
    0.31
    带åĽŀ
    0.30
    Activations Density 0.001%

    No Known Activations