INDEX

Explanations

in

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

transition

-0.28

iore

-0.26

.bmp

-0.25

å¾ħ

-0.25

nÃ§

-0.25

èĭ±çī¹

-0.25

 temps

-0.25

BIN

-0.24

BR

-0.24

vil

-0.24

POSITIVE LOGITS

æĭľ

0.29

 gÃ¼

0.26

 Loose

0.25

0.24

éĽĦ

0.24

SI

0.23

 spot

0.23

“

0.23

çĻ

0.23

Activations Density 0.006%

in

No Comments

No Known Activations