INDEX

Explanations

on

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

rog

-0.28

ropri

-0.26

station

-0.25

Guid

-0.25

 Guid

-0.25

 cris

-0.24

_guid

-0.24

æĵį

-0.24

 unle

-0.24

 station

-0.24

POSITIVE LOGITS

ARED

0.27

çļĦåį±å®³

0.25

ottes

0.25

CARD

0.25

arov

0.25

OTTOM

0.25

ancy

0.24

 averaged

0.23

tle

0.23

 drown

0.23

Activations Density 0.671%

on

No Known Activations