INDEX

Explanations

parenthesis and/or percentage

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 shoulders

-0.27

hani

-0.27

ets

-0.26

 DONE

-0.26

 Morr

-0.26

 done

-0.25

ones

-0.25

æĺŁæĺŁ

-0.25

DONE

-0.25

kinson

-0.24

POSITIVE LOGITS

äº®

0.25

Ã¡nd

0.25

 keeping

0.25

 lÆ°á»£ng

0.24

alu

0.24

¶Ī

0.24

(sl

0.24

èĥ§

0.23

/ui

0.23

è¸ī

0.23

Activations Density 0.001%

parenthesis and/or percentage

No Comments

No Known Activations