© 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. 41194
    Prev
    Next
    INDEX
    Explanations

    as

    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
    atoi
    -0.28
    enne
    -0.27
    äºĨå¤ļå°ij
    -0.27
    è¸Ŀ
    -0.26
    anio
    -0.25
    doors
    -0.25
    cba
    -0.25
     trùng
    -0.25
    QN
    -0.24
     scientists
    -0.24
    POSITIVE LOGITS
    Ỽt
    0.28
    VG
    0.27
    elman
    0.26
    Ä°R
    0.26
    åıijå±ķ缮æłĩ
    0.26
    åıijå±ķ空éĹ´
    0.26
    å¿«éĢŁåıijå±ķ
    0.25
    packet
    0.25
    allas
    0.25
     Gang
    0.25
    Activations Density 2.436%

    No Known Activations