© 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. 8894
    Prev
    Next
    INDEX
    Explanations

    take

    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
     hires
    -0.29
    appa
    -0.27
    elly
    -0.25
    mailto
    -0.24
     Reward
    -0.24
    lle
    -0.23
    çĮ¬
    -0.23
    约åIJĪ
    -0.23
    Č
    -0.23
    igger
    -0.23
    POSITIVE LOGITS
    plib
    0.27
    å´Ń
    0.26
    详ç»Ĩä»ĭç»į
    0.25
    ẫn
    0.25
    shape
    0.25
     shape
    0.25
     roots
    0.25
    ä»ĭç»į
    0.25
    åħ¹
    0.24
     reim
    0.24
    Activations Density 0.008%

    No Known Activations