© 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. 23170
    Prev
    Next
    INDEX
    Explanations

    elect

    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
     Aging
    -0.29
    год
    -0.28
     ageing
    -0.27
    onian
    -0.26
    sez
    -0.26
     aging
    -0.26
    èĢģåĮĸ
    -0.25
     век
    -0.25
    ourage
    -0.25
    çĺ¦
    -0.25
    POSITIVE LOGITS
     raid
    0.28
    apult
    0.27
    urement
    0.26
     raided
    0.25
    çļĦéĩįè¦ģæĢ§
    0.25
     raids
    0.24
    -any
    0.24
     architectural
    0.24
     carpet
    0.24
    HING
    0.24
    Activations Density 0.000%

    No Known Activations