INDEX

Explanations

also

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

PageIndex

-0.25

 oversee

-0.25

TickCount

-0.25

é£Łæ¬²

-0.25

 transit

-0.25

lop

-0.25

obo

-0.24

 gÃ¶rev

-0.24

 pubs

-0.24

arkin

-0.24

POSITIVE LOGITS

 Think

0.27

endale

0.26

æį®

0.25

enced

0.25

Think

0.25

 think

0.24

æļ´éľ²

0.24

æĶ¯

0.24

 Pink

0.23

Quarter

0.23

Activations Density 0.004%

also

No Comments

No Known Activations