© 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. 41286
    Prev
    Next
    INDEX
    Explanations

    distance units

    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
    ä¸īåįĥ
    -0.26
    angelo
    -0.26
    èĬ¸
    -0.25
    oker
    -0.25
     capita
    -0.24
    Ctl
    -0.24
    okin
    -0.24
    bps
    -0.24
    è¾¾
    -0.24
    çĪ±ç¾İ
    -0.24
    POSITIVE LOGITS
    æĶ¾å¿ĥ
    0.27
    oard
    0.27
    é£Ł
    0.26
     fore
    0.26
    esz
    0.26
    ä¸įä¿¡
    0.25
    Discovery
    0.25
    è¶ħåĩº
    0.25
    YPD
    0.24
    jet
    0.24
    Activations Density 0.471%

    No Known Activations