INDEX

Explanations

which

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

å¥½äºº

-0.29

åĽ½çİĭ

-0.26

CompleteListener

-0.25

Å¾e

-0.25

ibi

-0.25

Ã§e

-0.25

 BIOS

-0.24

RTP

-0.24

ItemAt

-0.24

kart

-0.24

POSITIVE LOGITS

 escal

0.25

 floated

0.24

igrated

0.24

èĢĢçľ¼

0.23

 milestones

0.23

IDO

0.23

chedulers

0.23

æ³Ĺ

0.23

 however

0.22

 spheres

0.22

Activations Density 0.012%

which

No Comments

No Known Activations