© 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. 31-TRANSCODER-HP
    7. 19275
    Prev
    Next
    INDEX
    Explanations

    D

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ло
    -0.30
    ney
    -0.28
    ertia
    -0.27
    Directed
    -0.27
    erg
    -0.27
    decl
    -0.26
     Directed
    -0.25
    htub
    -0.25
    :boolean
    -0.25
    ä½İä½į
    -0.25
    POSITIVE LOGITS
    æ²®
    0.29
     Saga
    0.25
    frag
    0.25
    éºĴ
    0.24
    åĭī
    0.24
    plural
    0.24
    çĶŁ
    0.24
    ivism
    0.24
    é²ĩ
    0.23
     bubbles
    0.23
    Activations Density 0.824%

    No Known Activations