© 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. 24-TRANSCODER-HP
    7. 149621
    Prev
    Next
    INDEX
    Explanations

    prot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı£è¢ĭ
    -0.29
     Fate
    -0.26
    stro
    -0.24
    istrib
    -0.24
    uir
    -0.24
    inar
    -0.23
    uts
    -0.23
    å¯IJ
    -0.23
    ÑģÑĥд
    -0.22
    çĭ¸
    -0.22
    POSITIVE LOGITS
    åħĪè¿Ľ
    0.30
    edx
    0.28
     pressure
    0.27
     heck
    0.27
    pressure
    0.27
    emics
    0.26
    èĥĮ
    0.25
    term
    0.25
    der
    0.25
    otyping
    0.24
    Activations Density 0.162%

    No Known Activations