INDEX

Explanations

s

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

olec

-0.27

 Transcript

-0.26

 Category

-0.26

(Category

-0.25

umed

-0.24

á»Ħ

-0.24

Ø±Ø²

-0.24

nell

-0.24

 nell

-0.24

turnstile

-0.23

POSITIVE LOGITS

 harmon

0.29

çĭŃ

0.27

uvw

0.26

elve

0.26

 interact

0.25

.GetSize

0.25

çĪ±äºº

0.24

éĿŀå¸¸å¥½

0.24

 like

0.24

å°¤åħ¶æĺ¯

0.24

Activations Density 0.662%

s

No Comments

No Known Activations