INDEX

Explanations

Philippines

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 replicated

-0.27

 Fine

-0.27

perfect

-0.26

æºľ

-0.26

 replic

-0.26

interp

-0.26

ascus

-0.26

Fine

-0.26

 MODEL

-0.25

Cake

-0.25

POSITIVE LOGITS

ä½Ļå®¶

0.28

bos

0.28

åĹŁ

0.27

stÃ¤nd

0.27

ç¾¤å²Ľ

0.26

antry

0.26

||↵

0.26

.sparse

0.25

å©ķ

0.25

bow

0.25

Activations Density 0.225%

Philippines

No Comments

No Known Activations