INDEX

Explanations

case

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

 case

-0.34

(case

-0.30

CASE

-0.30

case

-0.30

-case

-0.29

 cases

-0.29

Case

-0.28

èĺĳ

-0.28

_CASE

-0.28

 CASE

-0.28

POSITIVE LOGITS

emie

0.27

à¹ģà¸ĭ

0.25

Credits

0.25

 Thesis

0.24

(Key

0.24

Ã©ra

0.24

-Origin

0.24

Leh

0.24

enas

0.24

ral

0.24

Activations Density 0.192%

case

No Comments

No Known Activations