INDEX

Explanations

ud

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

Ð·Ð¾Ð½

-0.27

Ð¼Ð°ÑĢ

-0.27

Rated

-0.26

è¶£

-0.26

æĺ¯ä¸Ģéĥ¨

-0.25

éĿ¢ä¸Ĭ

-0.25

permalink

-0.25

-front

-0.24

 Academic

-0.24

Ð°ÑĢÐ°Ð¼

-0.24

POSITIVE LOGITS

çī¹æĿĥ

0.31

çĸ±

0.28

fÃ¶r

0.28

))->

0.26

åħļç»Ħä¹¦è®°

0.25

krit

0.25

 growing

0.25

gon

0.25

 grow

0.25

Fro

0.24

Activations Density 26.553%

ud

No Comments

No Known Activations