INDEX

Explanations

th

np_max-act · gemini-2.0-flash

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

Not in Any Lists

No Comments

Negative Logits

æľį

-0.28

ä¸ĥåįģ

-0.27

quite

-0.25

quit

-0.24

zÃ¡

-0.24

 sixty

-0.24

è·¨åº¦

-0.24

Ã¼cken

-0.24

åıªæľī

-0.23

ç®¡çĲĨä½ĵç³»

-0.23

POSITIVE LOGITS

 COMMON

0.24

ä¾¥å¹¸

0.24

-century

0.24

ë¡Ŀ

0.23

 dime

0.23

Ð¾Ð±ÑħÐ¾Ð´Ð¸Ð¼

0.23

presso

0.23

edBy

0.23

 Inner

0.22

eneral

0.22

Activations Density 0.044%

th

No Comments

No Known Activations