© 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. 14-TRANSCODER-HP
    7. 40060
    Prev
    Next
    INDEX
    Explanations

    bold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <small
    -0.28
     suggestions
    -0.27
    etto
    -0.27
     suggestion
    -0.24
     import
    -0.24
    }]↵
    -0.24
    Suggestions
    -0.23
    ora
    -0.23
    portunity
    -0.23
     instructions
    -0.23
    POSITIVE LOGITS
    /source
    0.25
    ogl
    0.24
    æİ
    0.24
    rophe
    0.24
     Indones
    0.24
    juan
    0.24
     drunk
    0.24
    :Number
    0.23
     Dutch
    0.23
    ç¾İ好çĶŁæ´»
    0.23
    Activations Density 0.093%

    No Known Activations