© 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. 109178
    Prev
    Next
    INDEX
    Explanations

    stand

    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
    s
    -0.26
    cko
    -0.25
     Last
    -0.25
    anto
    -0.25
     As
    -0.25
     Lever
    -0.25
    è®°å¾Ĺ
    -0.24
    oma
    -0.24
     Stored
    -0.24
     Disposable
    -0.24
    POSITIVE LOGITS
     dáºŃy
    0.29
    åħľ
    0.28
    çĹĺ
    0.27
    ÂŃing
    0.27
    æ½®
    0.27
    .Prop
    0.25
    heels
    0.25
    olini
    0.25
    овоÑĢ
    0.24
    代表大ä¼ļ
    0.24
    Activations Density 1.007%

    No Known Activations