INDEX

Explanations

Small increments or comparisons

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

çĶĺ

-0.27

agos

-0.25

fgang

-0.24

lim

-0.24

é«ĺè¾¾

-0.23

.Cancel

-0.23

rapid

-0.23

éĻĨç»Ń

-0.23

centration

-0.23

suite

-0.23

POSITIVE LOGITS

ç¨įå¾®

0.47

 slightly

0.47

 increment

0.44

 Increment

0.43

å¢ŀåĬł

0.42

increment

0.42

å¢ŀåĬłäºĨ

0.41

Increment

0.40

.increment

0.40

å¢ŀæ·»

0.39

Activations Density 0.004%

Small increments or comparisons

No Comments

No Known Activations