© 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. 32-TRANSCODER-HP
    7. 43026
    Prev
    Next
    INDEX
    Explanations

    bacterial research texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otto
    -0.28
    ourke
    -0.28
    infinity
    -0.26
    istra
    -0.25
     OTP
    -0.25
    å¸¦ä½ł
    -0.25
    lime
    -0.24
    ãĤ²
    -0.24
    _gateway
    -0.24
    esses
    -0.24
    POSITIVE LOGITS
    ELY
    0.33
    vy
    0.30
    çĪ±
    0.27
    FindBy
    0.26
    Vy
    0.25
    vae
    0.25
    epy
    0.25
    elve
    0.24
    fac
    0.24
    BS
    0.24
    Activations Density 0.003%

    No Known Activations