INDEX

Explanations

Names and specified locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

spl

-0.29

 intr

-0.27

ois

-0.26

 Gentle

-0.26

	null

-0.25

 null

-0.25

æľĪä¸Ń

-0.25

asures

-0.25

ä¾Ľ

-0.24

[r

-0.24

POSITIVE LOGITS

MASTER

0.31

/exec

0.28

 Operational

0.27

ä¸ŀ

0.27

/master

0.27

_Master

0.25

Unavailable

0.25

 Ones

0.25

ille

0.24

=subprocess

0.24

Activations Density 0.013%

Names and specified locations

No Comments

No Known Activations