© 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. 18-TRANSCODER-HP
    7. 88560
    Prev
    Next
    INDEX
    Explanations

    negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    表éĿ¢
    -0.30
    çľĭä¼¼
    -0.29
    ä½Ĩåį´
    -0.29
     but
    -0.27
     seemingly
    -0.27
    æĹ¢çĦ¶
    -0.27
    åıĪè¦ģ
    -0.27
    ãĤŃãĥ³
    -0.27
    충
    -0.27
    -but
    -0.26
    POSITIVE LOGITS
    riott
    0.28
     conf
    0.27
    zahl
    0.26
     cit
    0.25
    kea
    0.25
    asad
    0.24
    felt
    0.24
    dent
    0.24
    æł¸å¿ĥæĬĢæľ¯
    0.24
    使çĶ¨èĢħæĪĸ
    0.24
    Activations Density 52.214%

    No Known Activations