INDEX

Explanations

give

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å§Ķåī¯ä¹¦è®°

-0.27

 Pulitzer

-0.27

å½¼

-0.26

dis

-0.26

æĬ±çĿĢ

-0.25

çĺ°

-0.25

æİ¨èįĲéĺħè¯»

-0.25

åŁºæľ¬åİŁåĪĻ

-0.24

(debug

-0.23

WithOptions

-0.23

POSITIVE LOGITS

 Watkins

0.30

JT

0.28

oras

0.28

.$.

0.25

jun

0.25

WC

0.25

 fieldName

0.25

ioni

0.24

eren

0.24

wers

0.24

Activations Density 0.008%

give

No Comments

No Known Activations