INDEX

Explanations

rapid

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pain

-0.26

 Attention

-0.25

pain

-0.24

.stamp

-0.24

 Nature

-0.24

=zeros

-0.24

_$

-0.23

 pain

-0.23

usch

-0.23

mits

-0.23

POSITIVE LOGITS

 increasing

0.40

éļıçĿĢæĹ¶éĹ´

0.38

 rapidly

0.37

 progressing

0.37

 changing

0.37

 evolving

0.37

 growing

0.35

 expanding

0.35

 progress

0.34

 advancing

0.34

Activations Density 0.006%

rapid

No Comments

No Known Activations