© 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. 22682
    Prev
    Next
    INDEX
    Explanations

    It

    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
     numbered
    -0.27
    licated
    -0.27
    æ¯Ľ
    -0.26
    Ted
    -0.26
    èİ«
    -0.26
    ivid
    -0.25
     Hamm
    -0.25
    èĪĤ
    -0.25
    Tube
    -0.25
    $',
    -0.24
    POSITIVE LOGITS
    ог
    0.27
    олов
    0.26
     Mant
    0.26
    çľĩ
    0.25
    åĨħç§ij
    0.25
    ”
    0.24
    âĢ¦”
    0.24
    =%.
    0.24
    åĪĨæķ°
    0.24
    PUT
    0.23
    Activations Density 0.001%

    No Known Activations