© 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. 23813
    Prev
    Next
    INDEX
    Explanations

    marking calendars

    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
    ĵåIJį
    -0.26
     mankind
    -0.25
    rans
    -0.25
    CO
    -0.25
     геÑĢ
    -0.25
    essor
    -0.24
    helm
    -0.24
    åľ°çIJĥä¸Ĭ
    -0.24
     protected
    -0.24
     neutrality
    -0.24
    POSITIVE LOGITS
    [first
    0.28
    å°¤åħ¶æĺ¯åľ¨
    0.26
    uts
    0.26
    éĥ¨åĪĨåĨħ容
    0.26
     dames
    0.25
     Buf
    0.24
     pij
    0.24
    rost
    0.24
     Raqqa
    0.24
     ['-
    0.24
    Activations Density 0.001%

    No Known Activations