© 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. 25-TRANSCODER-HP
    7. 108334
    Prev
    Next
    INDEX
    Explanations

    permanently/temporarily

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     acad
    -0.25
     Mär
    -0.25
    stick
    -0.25
    yu
    -0.25
    ãĥĥãĥĹ
    -0.25
    yth
    -0.25
    å·¾
    -0.25
    cit
    -0.24
    hw
    -0.24
     amen
    -0.24
    POSITIVE LOGITS
     Disconnect
    0.27
     Dep
    0.26
     Affero
    0.26
    .setCursor
    0.26
    iales
    0.26
     disconnect
    0.26
    åĶ¾
    0.26
    å°±çŁ¥éģĵ
    0.25
     Independent
    0.24
     closest
    0.24
    Activations Density 0.223%

    No Known Activations