INDEX

Explanations

for

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

æĪĸèĢħåħ¶ä»ĸ

-0.27

ANEL

-0.26

.ibatis

-0.26

ç¦ģ

-0.26

 favoured

-0.25

å²Ĺ

-0.25

 recognise

-0.25

åħŃå¤§

-0.24

åļ

-0.24

ibel

-0.24

POSITIVE LOGITS

 precision

0.29

 userEmail

0.26

apas

0.26

PIO

0.26

 Precision

0.25

uario

0.25

isc

0.25

sen

0.24

oman

0.24

é¡¿

0.24

Activations Density 0.045%

for

No Comments

No Known Activations