© 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. 35-TRANSCODER-HP
    7. 40259
    Prev
    Next
    INDEX
    Explanations

    Legal cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Authentic
    -0.25
     Disposable
    -0.24
     iota
    -0.24
     constitu
    -0.24
     Primary
    -0.24
    Disposable
    -0.24
    .googleapis
    -0.24
     Shadows
    -0.24
     Tower
    -0.24
    atri
    -0.23
    POSITIVE LOGITS
    dk
    0.39
    mann
    0.39
    kov
    0.37
    heim
    0.35
    berg
    0.35
    mv
    0.34
    bp
    0.34
    feld
    0.33
    vb
    0.32
    mma
    0.32
    Activations Density 4.405%

    No Known Activations