© 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. 12-TRANSCODER-HP
    7. 22736
    Prev
    Next
    INDEX
    Explanations

    stop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ñe
    -0.29
     consistency
    -0.27
    ISON
    -0.26
     messy
    -0.26
    eing
    -0.25
     fists
    -0.25
    uktur
    -0.25
    @m
    -0.25
    forder
    -0.24
    rift
    -0.24
    POSITIVE LOGITS
    æİł
    0.31
     updater
    0.29
     rule
    0.28
     createState
    0.28
    çĪµ
    0.27
    amer
    0.26
    ullah
    0.26
    åķĨè´¸
    0.25
    Rule
    0.25
     iteration
    0.24
    Activations Density 0.002%

    No Known Activations