© 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. 32-TRANSCODER-HP
    7. 42983
    Prev
    Next
    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oni
    -0.28
    inth
    -0.27
    oke
    -0.27
     rather
    -0.27
     ever
    -0.26
    esk
    -0.26
    oning
    -0.26
    past
    -0.25
    ili
    -0.25
    ings
    -0.24
    POSITIVE LOGITS
     wanted
    0.34
    绯
    0.33
     relied
    0.29
     preferred
    0.28
     needed
    0.28
     required
    0.27
    ))->
    0.27
    needed
    0.27
    è¿ĺæĥ³
    0.26
    éľĢè¦ģçĶ¨åĪ°
    0.26
    Activations Density 0.002%

    No Known Activations