INDEX

Explanations

Highland

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

_SYM

-0.27

ÑĢÐ°ÑģÑĤ

-0.27

å¤§åľ°

-0.27

*)"

-0.26

å¯¹æĸ¹

-0.26

çıį

-0.25

.ActionListener

-0.25

@brief

-0.25

 unfavor

-0.24

åĪļ

-0.24

POSITIVE LOGITS

æ¸

0.32

 Fortress

0.27

 Hyper

0.26

 MacBook

0.25

 scratch

0.25

æīĪ

0.25

drop

0.25

Hyper

0.25

 Leaving

0.23

vac

0.23

Activations Density 0.109%

Highland

No Comments

No Known Activations