© 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. 22-TRANSCODER-HP
    7. 130740
    Prev
    Next
    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.28
    пÑĥÑĤ
    -0.24
    dux
    -0.24
    æĿ¯åŃIJ
    -0.24
     an
    -0.23
     prol
    -0.23
    regon
    -0.23
     pet
    -0.23
     áp
    -0.23
     Cop
    -0.23
    POSITIVE LOGITS
    _exact
    0.26
    åħ·ä½ĵåĨħ容
    0.26
    ifference
    0.26
    icolon
    0.25
    ays
    0.24
    'o
    0.24
    ÄĻż
    0.24
    å²Ķ
    0.24
    arking
    0.24
    .air
    0.23
    Activations Density 0.040%

    No Known Activations