INDEX

Explanations

No Explanations Found

New Auto-Interp

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

Negative Logits

äº§åŃ¦

-0.27

åįĴ

-0.26

InView

-0.25

gree

-0.25

å´¤

-0.24

å¼ºåĽ½

-0.24

 Prompt

-0.24

 Gord

-0.24

_nth

-0.24

æĬķèŀįèµĦ

-0.24

POSITIVE LOGITS

omi

0.28

Fre

0.27

.bz

0.26

 band

0.26

 persist

0.25

enc

0.25

çģ«çĦ°

0.25

ML

0.24

Lug

0.24

ish

0.24

Activations Density 0.049%

No Known Activations

This feature has no known activations.