INDEX

Explanations

delimiters

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

ä¼´ä¾£

-0.27

 fabric

-0.27

fabric

-0.27

.pages

-0.26

 pages

-0.25

æ¹Ľ

-0.25

å¹¿éĺĶçļĦ

-0.25

 tá»ī

-0.25

riere

-0.24

æ¨½

-0.24

POSITIVE LOGITS

 pinch

0.34

alo

0.28

çĤ¹äºĨ

0.26

ä¹¾

0.24

|M

0.24

è¡®

0.24

elic

0.24

enheim

0.24

æ³»

0.24

@m

0.24

Activations Density 0.006%

delimiters

No Comments

No Known Activations