© 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. 23-TRANSCODER-HP
    7. 24794
    Prev
    Next
    INDEX
    Explanations

    'use strict'

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (pe
    -0.26
    solete
    -0.25
    icked
    -0.25
    .Companion
    -0.25
    ав
    -0.25
    .fe
    -0.24
     Narendra
    -0.24
    mue
    -0.24
     Protector
    -0.24
    TRACT
    -0.24
    POSITIVE LOGITS
    å¼Ģåĩº
    0.26
    izia
    0.25
    izen
    0.25
    izer
    0.24
    zier
    0.24
    setId
    0.23
    åĬ
    0.23
    ambre
    0.23
     metal
    0.23
     symmetry
    0.23
    Activations Density 0.005%

    No Known Activations