© 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. 107320
    Prev
    Next
    INDEX
    Explanations

    medical or technical topics

    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
     nonetheless
    -0.28
    rong
    -0.28
    vers
    -0.26
    ildo
    -0.26
     Timeline
    -0.25
    crm
    -0.25
    æķıæĦŁ
    -0.25
    æľĢåıĹ欢è¿İ
    -0.24
    otland
    -0.24
    nga
    -0.24
    POSITIVE LOGITS
    /exp
    0.26
    次è¦ģ
    0.25
    å¹ħ
    0.25
    /un
    0.24
    tails
    0.24
     rehe
    0.24
    åĮł
    0.24
    дÑĥ
    0.24
    -roll
    0.24
    åĮłå¿ĥ
    0.23
    Activations Density 1.120%

    No Known Activations