INDEX

Explanations

period

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riend

-0.27

Coder

-0.26

åĭĩå£«

-0.25

ÑĥÑħ

-0.25

 Spotlight

-0.24

bucket

-0.24

ugg

-0.24

 Libert

-0.24

ãģĪ

-0.24

çķĻä½ı

-0.23

POSITIVE LOGITS

 owes

0.27

äºĭåħ³

0.27

JOR

0.25

æľ¬èº«

0.25

ertino

0.25

 moderately

0.24

ä¸įæĺ¯å¾Ī

0.24

 moderate

0.23

 VERY

0.23

/fs

0.23

Activations Density 0.016%

period

No Comments

No Known Activations