INDEX

Explanations

Technical/code related topics

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ocol

-0.29

 blur

-0.29

rust

-0.27

æĬ¥

-0.27

lik

-0.26

æĹ¥çħ§

-0.26

synthesize

-0.25

bl

-0.25

astype

-0.25

elist

-0.25

POSITIVE LOGITS

.JSON

0.26

Åĥ

0.26

æĭħ

0.25

åĽłç´ł

0.25

trand

0.25

-envelope

0.25

ä¼Ĭ

0.25

ennis

0.25

é¢ł

0.24

"#"

0.24

Activations Density 0.023%

Technical/code related topics

No Comments

No Known Activations