INDEX

Explanations

protocols and medical procedures

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

åĩ¡

-0.28

 targets

-0.25

 keeper

-0.25

":[

-0.24

ä¹Łä¸įåı¯èĥ½

-0.24

sez

-0.24

_targets

-0.24

ovah

-0.23

reich

-0.23

keeper

-0.23

POSITIVE LOGITS

 benefit

0.26

å½ķåĥı

0.26

èĢĹ

0.26

atern

0.25

perimental

0.25

ATER

0.25

bli

0.25

è¾ķ

0.24

roperty

0.24

(record

0.23

Activations Density 0.003%

protocols and medical procedures

No Comments

No Known Activations