© 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. 57511
    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
    eps
    -0.28
    寻常
    -0.28
    issing
    -0.26
    æ½Ń
    -0.26
     eps
    -0.26
     Fra
    -0.25
    æĺ¯æĪij们
    -0.24
    abs
    -0.24
    çĻ¾åĪĨä¹ĭ
    -0.24
     Grass
    -0.23
    POSITIVE LOGITS
     consider
    0.32
     carefully
    0.31
     retiring
    0.29
     believing
    0.28
     accepting
    0.28
     believe
    0.27
     resh
    0.27
    认为
    0.27
     trusting
    0.26
     thought
    0.26
    Activations Density 0.004%

    No Known Activations