INDEX

Explanations

II

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 dividends

-0.27

debug

-0.27

èĪĤ

-0.25

_spin

-0.25

 debug

-0.25

)="

-0.25

ermann

-0.25

*n

-0.24

dden

-0.24

adia

-0.24

POSITIVE LOGITS

kish

0.30

çļĦåŃ¦ä¹ł

0.26

vla

0.26

 Mats

0.25

çļĦä½ľçĶ¨

0.25

æ²¦

0.25

 Ashe

0.25

lis

0.25

_lens

0.25

sik

0.24

Activations Density 0.006%

II

No Comments

No Known Activations