© 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. 14-TRANSCODER-HP
    7. 40108
    Prev
    Next
    INDEX
    Explanations

    English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itat
    -0.29
    elts
    -0.27
    rit
    -0.27
    æĿ°
    -0.25
     former
    -0.25
    mit
    -0.25
     FAC
    -0.24
     ear
    -0.24
    åĦ¿å¥³
    -0.24
    inged
    -0.24
    POSITIVE LOGITS
     witnesses
    0.29
     witness
    0.29
    èºı
    0.27
    çĺĹ
    0.27
    çħ§äº®
    0.25
    ĶåĽŀ
    0.24
     Witness
    0.24
    å±Ĥå±Ĥ
    0.23
    POSIT
    0.23
    -proxy
    0.23
    Activations Density 0.196%

    No Known Activations