INDEX

Explanations

ori

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

 AppBundle

-0.28

apas

-0.27

 abbrev

-0.27

Ĥ¹

-0.25

æľįåĬ¡è´¨éĩı

-0.25

iento

-0.25

çĹ°

-0.25

 Rowe

-0.24

æľįåĬ¡æ°´å¹³

-0.24

 ìĤ´ìķĦ

-0.24

POSITIVE LOGITS

å«ļ

0.28

æĺ¯æĪĳçļĦ

0.27

ÙĬØ±ÙĬ

0.26

-mask

0.25

icity

0.25

ellation

0.25

Cd

0.25

amy

0.25

 litt

0.24

acic

0.24

Activations Density 0.009%

ori

No Comments

No Known Activations