INDEX

Explanations

ink

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

parcel

-0.26

ilib

-0.25

ORMAL

-0.25

 ground

-0.25

åħĥæĹ¦

-0.25

ju

-0.24

çļĦäººçĶŁ

-0.24

åľ°éĿ¢

-0.24

jure

-0.23

iones

-0.23

POSITIVE LOGITS

æĪĸè®¸æĺ¯

0.31

åı¯èĥ½æĺ¯

0.30

ä¹Łè®¸æĺ¯

0.26

æĪĸèĢħåħ¶ä»ĸ

0.26

ytt

0.26

eps

0.25

combe

0.25

é¥´

0.25

ying

0.25

 requestOptions

0.25

Activations Density 0.009%

ink

No Comments

No Known Activations