INDEX

Explanations

The

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

å®¸

-0.35

borough

-0.28

cms

-0.28

è¶ĭåĬ¿

-0.27

ä»¥åĲİ

-0.27

ä¹¡éķĩ

-0.26

ton

-0.25

 dicks

-0.24

$table

-0.24

Seq

-0.24

POSITIVE LOGITS

ivy

0.27

ITA

0.27

andal

0.26

Ike

0.25

 somew

0.25

ITE

0.24

 Randy

0.24

æĤĶ

0.24

ita

0.24

flate

0.24

Activations Density 0.002%

The

No Comments

No Known Activations