INDEX

Explanations

pale

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

etz

-0.28

éļı

-0.26

fix

-0.26

 ordinary

-0.25

etting

-0.25

 Bison

-0.25

rior

-0.25

ÑĥÐ³

-0.24

<HTML

-0.24

.lat

-0.24

POSITIVE LOGITS

ä¸ĢåĪĨéĴŁ

0.28

ioc

0.28

 delt

0.27

elve

0.26

cached

0.26

è¿Ī

0.26

ÑĢÑĥ

0.26

 cach

0.25

æ¯ıä¸Ģä½į

0.25

è´£ç¼ĸ

0.24

Activations Density 0.092%

pale

No Comments

No Known Activations