© 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. 30-TRANSCODER-HP
    7. 95425
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Version
    -0.28
    æŃ£
    -0.28
    	Version
    -0.28
    versions
    -0.28
    -version
    -0.27
    arnation
    -0.27
    avin
    -0.26
    -Version
    -0.26
    FileVersion
    -0.26
    _Version
    -0.24
    POSITIVE LOGITS
    çĶµåķĨå¹³åı°
    0.29
     Templ
    0.28
     Cert
    0.27
    失
    0.27
    =temp
    0.27
    aget
    0.26
    UGH
    0.26
    OrFail
    0.25
    Either
    0.25
    åĪ°ä½į
    0.25
    Activations Density 0.882%

    No Known Activations