INDEX

Explanations

code and parentheses

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 elsewhere

-0.28

 Networks

-0.26

hog

-0.25

 perms

-0.25

 further

-0.25

urf

-0.24

 continue

-0.24

 continues

-0.24

é¦

-0.24

 above

-0.24

POSITIVE LOGITS

 gÃ³

0.32

Isl

0.28

çľ¼åīįçļĦ

0.26

bitset

0.26

åĲ«æľī

0.25

|#

0.25

åıĭæĥħéĵ¾æİ¥

0.25

å¤Ħç½®

0.23

 fick

0.23

iji

0.23

Activations Density 7.182%

code and parentheses

No Comments

No Known Activations