© 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. 107397
    Prev
    Next
    INDEX
    Explanations

    drive/drives

    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
    ly
    -0.30
    ness
    -0.29
    æ·¡åĮĸ
    -0.26
    ifest
    -0.25
    herit
    -0.25
    ç½ijé¦ĸ页
    -0.25
    -facing
    -0.24
    elic
    -0.23
    ipse
    -0.23
    agog
    -0.23
    POSITIVE LOGITS
    ors
    0.32
     manufact
    0.26
    ings
    0.26
    brains
    0.25
     Carpenter
    0.25
    èı°
    0.24
    ÂŃing
    0.23
     organisation
    0.23
    丼
    0.23
     smoked
    0.23
    Activations Density 0.350%

    No Known Activations