INDEX

Explanations

from

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

æłĩ

-0.31

æĮĸæİĺ

-0.28

 abdom

-0.27

çĲīçĴĥ

-0.25

æģ¯

-0.25

 guarding

-0.25

çĪ±å¥½

-0.25

 incidence

-0.25

 melody

-0.25

çĶµåŃĲä¿¡æģ¯

-0.24

POSITIVE LOGITS

å¾Ĺç½ª

0.33

bpp

0.32

acey

0.29

.sap

0.26

æĶ¯è¡Į

0.26

ulerAngles

0.25

scp

0.25

inja

0.25

scp

0.24

æľĪä»¥æĿ¥

0.24

Activations Density 0.013%

from

No Comments

No Known Activations