INDEX

Explanations

internet data

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

Ã³d

-0.26

æĪĸèĢħæĺ¯

-0.26

rix

-0.25

åįıè®®

-0.25

rick

-0.25

pek

-0.25

æĪĸæĺ¯

-0.23

éľ²

-0.23

rost

-0.23

 Packet

-0.23

POSITIVE LOGITS

ickers

0.28

 mover

0.25

Ä±klÄ±

0.25

EFR

0.25

ivor

0.25

ä¸ĭä¸Ģç¯ĩ

0.24

ensex

0.24

inalg

0.24

åħ³

0.24

 Regions

0.23

Activations Density 0.000%

internet data

No Comments

No Known Activations