© 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. 30-TRANSCODER-HP
    7. 96305
    Prev
    Next
    INDEX
    Explanations

    ant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATORS
    -0.28
    tron
    -0.27
    iado
    -0.27
    çķĻ
    -0.26
    è¿Ļåľº
    -0.26
    åı¯è§Ĩ
    -0.26
     detr
    -0.26
    åľº
    -0.26
     mob
    -0.26
    çī¡
    -0.25
    POSITIVE LOGITS
    IFA
    0.31
    lane
    0.25
    次
    0.25
     quanto
    0.25
    linkplain
    0.25
    abyrinth
    0.25
    nP
    0.24
    CSR
    0.24
    oward
    0.24
    guild
    0.24
    Activations Density 0.919%

    No Known Activations