© 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. 8202
    Prev
    Next
    INDEX
    Explanations

    the

    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
     conseg
    -0.25
    åĶ¯
    -0.25
    ikel
    -0.24
    sig
    -0.24
    iguiente
    -0.23
    getClient
    -0.23
    æķĻæ¡Ī
    -0.23
     irr
    -0.23
    noch
    -0.23
    avings
    -0.23
    POSITIVE LOGITS
     organism
    0.42
     agency
    0.41
     institution
    0.40
     entity
    0.39
     organ
    0.39
    æľºæŀĦ
    0.39
     creatures
    0.38
     device
    0.37
    åĻ¨å®ĺ
    0.36
     molecule
    0.36
    Activations Density 0.003%

    No Known Activations