© 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. 39959
    Prev
    Next
    INDEX
    Explanations

    sticky/adhesive

    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
    arest
    -0.27
    è§Ĥ
    -0.25
    ardon
    -0.25
    icle
    -0.25
    lez
    -0.24
     PC
    -0.24
    ront
    -0.23
    imple
    -0.23
    _DRIVE
    -0.23
    allen
    -0.23
    POSITIVE LOGITS
     catch
    0.30
    elan
    0.27
    usement
    0.27
    æĽ³
    0.26
    çļĦä¸Ģåijĺ
    0.26
    ropy
    0.25
     Catch
    0.25
    apus
    0.25
    lse
    0.25
    .@
    0.24
    Activations Density 0.377%

    No Known Activations