INDEX

Explanations

length measurements

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

oplan

-0.31

ocaust

-0.28

Pot

-0.26

 Waters

-0.26

Vol

-0.25

opia

-0.25

æ½ľ

-0.25

æĬĢå·§

-0.25

pot

-0.24

Vol

-0.24

POSITIVE LOGITS

ENTA

0.27

quential

0.27

-lang

0.26

çĥĻ

0.26

ntag

0.25

iese

0.25

enses

0.25

ixin

0.25

.qq

0.24

thora

0.24

Activations Density 0.073%

length measurements

No Comments

No Known Activations