INDEX

Explanations

record

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

ichel

-0.27

_lite

-0.26

aleigh

-0.25

 unborn

-0.25

 steam

-0.25

èģĨ

-0.25

isclosed

-0.24

marvin

-0.24

à¹Ģà¸«à¸¥

-0.24

ocz

-0.24

POSITIVE LOGITS

obar

0.29

å¤§å®¶

0.28

ward

0.28

èĬĴ

0.28

au

0.27

å°½

0.26

Nah

0.26

table

0.26

å·½

0.25

..

0.24

Activations Density 0.008%

record

No Comments

No Known Activations