INDEX

Explanations

contrast

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orton

-0.27

 Counter

-0.26

 doing

-0.25

 conclus

-0.25

chn

-0.24

ores

-0.24

loo

-0.24

#w

-0.24

asn

-0.24

 Complex

-0.23

POSITIVE LOGITS

spaces

0.27

SENS

0.26

ulant

0.25

-any

0.25

ÐºÐµ

0.24

htdocs

0.24

Nature

0.23

duk

0.23

é¼ĵ

0.23

æ¶Ī

0.23

Activations Density 46.022%

contrast

No Comments

No Known Activations