© 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. 33-TRANSCODER-HP
    7. 54422
    Prev
    Next
    INDEX
    Explanations

    magn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngr
    -0.30
     magn
    -0.27
     weblog
    -0.27
    tsy
    -0.26
    bearing
    -0.26
    åľ°å¸¦
    -0.26
     Intercept
    -0.25
     Merc
    -0.25
     merit
    -0.25
    BlockSize
    -0.25
    POSITIVE LOGITS
    IC
    0.35
    ec
    0.33
    еÑĤ
    0.31
    us
    0.31
    Et
    0.31
    as
    0.31
    åŃIJ
    0.29
    æĸ¯
    0.29
    ic
    0.29
    ata
    0.28
    Activations Density 0.010%

    No Known Activations