© 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. 22873
    Prev
    Next
    INDEX
    Explanations

    yps

    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
     dri
    -0.28
    ái
    -0.28
     constructions
    -0.27
     shovel
    -0.26
    Ĥ¤
    -0.26
     taste
    -0.26
     drive
    -0.26
    åij³
    -0.25
     opposed
    -0.25
    [][
    -0.25
    POSITIVE LOGITS
     bund
    0.33
    upert
    0.32
    acency
    0.29
    ensible
    0.29
    ä»ĺåĩº
    0.26
    anny
    0.25
    iments
    0.24
    (plan
    0.24
    åĪĨç±»
    0.24
    irement
    0.24
    Activations Density 0.003%

    No Known Activations