© 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. 40853
    Prev
    Next
    INDEX
    Explanations

    honor

    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
    çªĥ
    -0.28
     AQ
    -0.26
     visibility
    -0.25
    onaut
    -0.25
    isers
    -0.24
    pressed
    -0.24
     hypocrisy
    -0.24
     eg
    -0.24
    iri
    -0.23
    icare
    -0.23
    POSITIVE LOGITS
    ĵį
    0.25
    elim
    0.25
    æĸ¹å¼ıè¿Ľè¡Į
    0.25
    强奸
    0.24
    ãĤ¬ãĥ³
    0.23
    areth
    0.23
    ollow
    0.23
    LAT
    0.22
    alin
    0.22
    endar
    0.22
    Activations Density 1.459%

    No Known Activations