INDEX

Explanations

music and language

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

 singleton

-0.28

singleton

-0.28

(tags

-0.27

achten

-0.26

Ã¤cht

-0.26

æľ¬åľŁ

-0.25

.Tags

-0.25

 tags

-0.25

Ð¶Ð°

-0.25

 leven

-0.25

POSITIVE LOGITS

 Warsaw

0.27

 thresholds

0.27

riday

0.25

åĵķ

0.25

 èĩ

0.24

äººä¸º

0.24

stras

0.24

ldb

0.24

åĩºçīĪ

0.23

Ð°Ð½Ð¸

0.23

Activations Density 0.021%

music and language

No Comments

No Known Activations