© 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. 89797
    Prev
    Next
    INDEX
    Explanations

    items needed

    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
    inkle
    -0.27
    >j
    -0.26
    clid
    -0.26
    çĿIJ
    -0.26
    ÑĤов
    -0.25
    'clock
    -0.25
    ogui
    -0.25
    éļ¨æĻĤ
    -0.24
    jid
    -0.24
    prime
    -0.24
    POSITIVE LOGITS
    Scr
    0.25
    .assertThat
    0.25
    对æ¯Ķ
    0.25
    Ç¿
    0.25
     Compar
    0.25
    opp
    0.24
    AE
    0.24
     Rather
    0.24
    _PULL
    0.24
     scrutin
    0.24
    Activations Density 6.024%

    No Known Activations