© 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. 12-TRANSCODER-HP
    7. 23012
    Prev
    Next
    INDEX
    Explanations

    Computer commands and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ches
    -0.29
    -pos
    -0.26
    gun
    -0.26
    istas
    -0.25
    以ä¸Ĭ
    -0.24
    pañ
    -0.24
    欢è¿İæĤ¨
    -0.23
    IEWS
    -0.23
    çĪ±äºº
    -0.23
    chan
    -0.23
    POSITIVE LOGITS
    çģı
    0.30
     withheld
    0.26
    æłĩå¿Ĺ
    0.25
    -minus
    0.24
    oby
    0.24
    èĤ½
    0.24
    åĴĮåľ°åĮº
    0.23
     prat
    0.23
     Mare
    0.23
     discontinued
    0.23
    Activations Density 0.004%

    No Known Activations