INDEX

Explanations

web addresses

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OC

-0.32

owe

-0.29

Node

-0.28

OC

-0.28

OM

-0.28

Breaking

-0.27

.mit

-0.26

 Node

-0.26

 Surround

-0.26

 Junk

-0.26

POSITIVE LOGITS

ä¼Ĭæĸ¯

0.26

isible

0.26

åıī

0.25

avors

0.23

å¤Ł

0.23

iasi

0.23

 forall

0.23

çĥĥ

0.23

åłĨ

0.23

.pages

0.23

Activations Density 0.431%

web addresses

No Comments

No Known Activations