INDEX

Explanations

Beginning of a process

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

 Reflex

-0.31

\db

-0.28

 unreachable

-0.26

ilian

-0.26

ICC

-0.25

ç®¡åĪ¶

-0.25

struk

-0.25

 reflex

-0.25

ADR

-0.25

|#

-0.24

POSITIVE LOGITS

_examples

0.30

Examples

0.28

unda

0.28

PREC

0.26

æ¯«

0.26

Prec

0.25

_prec

0.25

 Durham

0.25

 Prec

0.25

 Examples

0.24

Activations Density 0.827%

Beginning of a process

No Comments

No Known Activations