INDEX

Explanations

technical text

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

 supervision

-0.27

 Schwartz

-0.26

.getResponse

-0.25

 automation

-0.25

cus

-0.24

rand

-0.24

åĬ³

-0.23

_TUN

-0.23

 $↵

-0.23

å¤į

-0.23

POSITIVE LOGITS

ç§¯

0.33

ç©į

0.32

ä¹±è±¡

0.28

Impossible

0.27

æľĢéļ¾

0.27

 Impossible

0.26

èĢģå®ŀ

0.25

ç§¯ç´¯

0.25

Elim

0.24

æ¯Ķè¾ĥå¥½

0.24

Activations Density 5.743%

technical text

No Comments

No Known Activations