© 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. 57683
    Prev
    Next
    INDEX
    Explanations

    chemistry/ material science papers

    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
     lives
    -0.28
    第ä¸Ģæī¹
    -0.27
    rain
    -0.26
    ×Ļק×Ķ
    -0.26
    é¦ĸæī¹
    -0.25
    {//
    -0.25
    åħ¬åħ±åį«çĶŁ
    -0.24
    ದ
    -0.24
     flop
    -0.24
    eca
    -0.24
    POSITIVE LOGITS
    ä¸ĩ个
    0.29
    ucose
    0.28
     reference
    0.27
    ⾦
    0.26
     randomized
    0.26
    éĥ¨åĪĨåĨħ容
    0.26
     componentName
    0.26
    otime
    0.26
    ç»ĻåĬĽ
    0.26
    ighth
    0.25
    Activations Density 0.032%

    No Known Activations