INDEX

Explanations

timestamps

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

leg

-0.27

leg

-0.25

afa

-0.25

 inventor

-0.25

æİ°

-0.24

å¤©å¤©

-0.24

_probe

-0.24

éĤ

-0.24

-leg

-0.24

æĲĵ

-0.23

POSITIVE LOGITS

åŀĤ

0.28

å®īåİ¿

0.28

Elm

0.27

åĽ½å®ī

0.27

inf

0.26

ä¹Ŀå¹´

0.26

ÑĤÐ¾Ð½

0.26

ector

0.25

è¯´å¾Ĺ

0.25

alement

0.25

Activations Density 1.829%

timestamps

No Comments

No Known Activations