INDEX

Explanations

of

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isnan

-0.28

odiac

-0.28

çķİ

-0.26

pine

-0.26

æĥ§

-0.26

ksam

-0.25

èļ¤

-0.25

ç¬¬äºĮä¸ª

-0.24

SDS

-0.24

{s

-0.24

POSITIVE LOGITS

ater

0.26

 explanatory

0.25

âĶĢ

0.24

--↵↵

0.24

Origin

0.23

 Expanded

0.23

 origin

0.23

!--

0.23

alu

0.23

 deutsch

0.23

Activations Density 0.002%

of

No Comments

No Known Activations