INDEX

Explanations

Averages

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¦ģä¹Ī

-0.26

agne

-0.26

è§£çŃĶ

-0.26

ufe

-0.26

Ã¨me

-0.25

kd

-0.25

ãĥĽãĥ¼ãĥł

-0.25

ä¸ĭåįĬ

-0.25

åĶ®

-0.24

ÑģÐ¾Ð»

-0.24

POSITIVE LOGITS

 Rosenstein

0.30

/Library

0.28

loid

0.26

 grounding

0.26

ockets

0.26

é£²ãģ¿

0.25

å®Īä½ı

0.24

è¶Ĭé«ĺ

0.24

ocket

0.24

 tortured

0.24

Activations Density 3.325%

Averages

No Comments

No Known Activations