INDEX

Explanations

semicolon

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

SENS

-0.30

-toggler

-0.30

çİ°ä»»

-0.29

dbname

-0.28

å«ļ

-0.27

extends

-0.26

æĮīæĹ¶

-0.25

 datum

-0.25

æĦı

-0.25

ARAM

-0.24

POSITIVE LOGITS

ine

0.29

 Origins

0.28

olly

0.26

åĬ³

0.25

inha

0.25

 Remain

0.25

ar

0.25

 remaining

0.25

INE

0.24

.exp

0.24

Activations Density 0.000%

semicolon

No Comments

No Known Activations