INDEX

Explanations

family relationships

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Destroyed

-0.27

å¾ĹåĪĨ

-0.24

weed

-0.24

_mutex

-0.24

ointments

-0.24

umo

-0.24

_Pre

-0.23

_dev

-0.23

rott

-0.23

 outr

-0.23

POSITIVE LOGITS

-vertical

0.27

 sink

0.25

icit

0.25

sit

0.25

arcy

0.24

 Vertical

0.24

 Continental

0.23

sink

0.23

 Plains

0.23

STITUTE

0.23

Activations Density 0.002%

family relationships

No Comments

No Known Activations