© 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. 25-TRANSCODER-HP
    7. 107498
    Prev
    Next
    INDEX
    Explanations

    temperature in scientific context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ú
    -0.28
    lord
    -0.27
    overn
    -0.26
     Cons
    -0.26
     arms
    -0.25
     ÑģÑģÑĭл
    -0.25
     Label
    -0.25
    View
    -0.25
    rms
    -0.24
     coming
    -0.24
    POSITIVE LOGITS
    eki
    0.33
     nature
    0.27
     Claus
    0.27
     por
    0.26
     resil
    0.25
    .Stop
    0.25
    rok
    0.25
    rien
    0.25
    大èĩªçĦ¶
    0.25
    enity
    0.24
    Activations Density 0.900%

    No Known Activations