© 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. 40608
    Prev
    Next
    INDEX
    Explanations

    Places

    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
     coop
    -0.26
    åIJĪä½ľ
    -0.25
    <=$
    -0.25
    waters
    -0.25
    ocratic
    -0.25
    æĽĿåħī
    -0.24
    åıĤå±ķ
    -0.24
    Ont
    -0.24
    å®īå±ħ
    -0.24
    avia
    -0.23
    POSITIVE LOGITS
    egan
    0.26
    entric
    0.25
    itals
    0.25
    AGER
    0.24
    WARE
    0.24
    wh
    0.24
    General
    0.23
     Worth
    0.23
    ystems
    0.23
    nc
    0.23
    Activations Density 2.316%

    No Known Activations