INDEX

Explanations

technical, physics related processes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

DOUBLE

-0.29

Ð±Ð°Ð½

-0.27

defense

-0.27

 nest

-0.27

TERN

-0.26

enet

-0.26

Derived

-0.25

 Execution

-0.25

äººå¯¿

-0.25

 pros

-0.24

POSITIVE LOGITS

awei

0.29

 corrections

0.27

è½²

0.26

 booths

0.26

mcc

0.26

edback

0.26

èĦ±ç¦»

0.26

å¤§åıĶ

0.25

å¸¦æĿ¥çļĦ

0.25

ä¸Ģä¸ªä¸ª

0.24

Activations Density 0.030%

technical, physics related processes

No Comments

No Known Activations