INDEX

Explanations

breath

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

ivot

-0.27

 Held

-0.26

å¹³

-0.26

åŃ¦ä¹ł

-0.25

BT

-0.25

 passage

-0.25

 shed

-0.25

 strang

-0.24

 Upper

-0.24

 Bowman

-0.24

POSITIVE LOGITS

 lump

0.27

Ã¤u

0.26

oxide

0.25

icals

0.25

_EXTERN

0.25

adium

0.24

çĶµæµģ

0.24

 vite

0.24

 COPYING

0.24

_handles

0.24

Activations Density 0.009%

breath

No Comments

No Known Activations