© 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. 20-TRANSCODER-HP
    7. 107179
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lers
    -0.25
    _INLINE
    -0.24
    #.
    -0.24
    帮åĬ©ä¼ģä¸ļ
    -0.24
    ages
    -0.24
    足以
    -0.24
    _InitStructure
    -0.24
    @qq
    -0.23
    landers
    -0.23
    ONENT
    -0.23
    POSITIVE LOGITS
    TOT
    0.28
     riot
    0.26
    urn
    0.25
    BO
    0.24
    éĢĥ
    0.24
    è¿Ļ家åħ¬åı¸
    0.24
    tel
    0.23
    å®Į好
    0.23
    _effects
    0.23
    verb
    0.23
    Activations Density 9.613%

    No Known Activations

    This feature has no known activations.