INDEX

Explanations

Proper nouns and services

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

ometrics

-0.27

bru

-0.27

 credible

-0.25

çĲīçĴĥ

-0.25

 isolation

-0.24

 inclusive

-0.24

.locale

-0.24

.Errors

-0.24

 suburb

-0.24

mar

-0.23

POSITIVE LOGITS

å¼¶

0.28

-release

0.27

äºĭåħĪ

0.26

ÑģÑĤÐ²ÐµÐ½Ð½Ð¾

0.26

èĬ¨

0.26

 nghiá»ĩm

0.26

 RELEASE

0.25

ensburg

0.25

çĴĭ

0.25

æ±²

0.25

Activations Density 0.001%

Proper nouns and services

No Comments

No Known Activations