INDEX

Explanations

code or foreign language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fib

-0.28

elib

-0.28

AAP

-0.28

èĭķ

-0.27

href

-0.27

Ð°Ð¹Ð½

-0.27

fiber

-0.26

 Fiber

-0.25

 fibers

-0.25

 hydrogen

-0.25

POSITIVE LOGITS

mal

0.26

Chunk

0.25

 chunk

0.24

åĪĨæīĭ

0.24

çĽ¸åħ³æĶ¿çŃĸ

0.23

è¯Ģ

0.23

åĪĨ

0.23

Submit

0.23

acerb

0.23

æ¬¾

0.23

Activations Density 0.001%

code or foreign language

No Comments

No Known Activations