INDEX

Explanations

enforcement

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

ä¸įéĢļ

-0.28

 Altern

-0.27

pty

-0.27

 sino

-0.26

ìĹ´

-0.25

 torture

-0.24

åĪ¶ä½ľ

-0.24

eneg

-0.23

 Cornel

-0.23

 nguyá»ĩn

-0.23

POSITIVE LOGITS

èĽ¹

0.29

ospace

0.29

=key

0.27

å¼¹ç°§

0.26

Pause

0.25

 deserving

0.25

æķĪçĽĬ

0.25

dued

0.25

ead

0.24

è¶£

0.24

Activations Density 0.002%

enforcement

No Comments

No Known Activations