© 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. 41039
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    +len
    -0.28
    åĵ®
    -0.28
    çĹĥ
    -0.26
     confort
    -0.26
    ffer
    -0.26
    èĦĸ
    -0.26
    ç¬Ķè®°
    -0.25
    éĩijåŃĹå¡Ķ
    -0.25
    istinguished
    -0.24
    å¼Ģåı£
    -0.24
    POSITIVE LOGITS
    åħ¶ä¸Ńä¸Ģ个
    0.33
    coe
    0.30
    èĶ½
    0.29
    nic
    0.28
    æĺ¼
    0.27
    çĿ¡
    0.27
    ç»ı纪
    0.26
    quel
    0.26
    ecast
    0.25
    frey
    0.25
    Activations Density 7.090%

    No Known Activations