INDEX

Explanations

(

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 exhaustive

-0.28

uckets

-0.27

 anthrop

-0.26

lud

-0.26

 biological

-0.26

cepts

-0.25

&view

-0.25

 recept

-0.25

æľīåĲįçļĦ

-0.24

èĩªæ²»

-0.24

POSITIVE LOGITS

ernal

0.30

Ð¸Ð»Ð¸

0.29

Ear

0.29

é¢ļ

0.27

åĪĨæķ°çº¿

0.26

_party

0.26

Ð¸Ð»Ð°

0.26

ä½ĵéĩį

0.25

å¾µ

0.25

ÑħÐ¾

0.24

Activations Density 0.009%

(

No Comments

No Known Activations