© 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. 40125
    Prev
    Next
    INDEX
    Explanations

    equivalence

    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
     frequencies
    -0.28
    é©Ń
    -0.28
    æIJŀ
    -0.27
    ynth
    -0.25
    iblings
    -0.25
     Æ°u
    -0.25
    æĴĴ
    -0.25
    æĹ©
    -0.24
     Frequ
    -0.24
    横
    -0.24
    POSITIVE LOGITS
     sense
    0.29
    å®īå±ħ
    0.26
     Sense
    0.26
    ãĤŃãĥ³ãĤ°
    0.25
    itorio
    0.25
    ındaki
    0.25
    otros
    0.24
    stin
    0.24
    ç¥ĵ
    0.24
    æĬĬä»ĸ
    0.24
    Activations Density 0.735%

    No Known Activations